This will be interesting for a few reasons. First, depending on where the median pricing settles w/ 3rd party providers will tell us what it costs to serve a 3T model. Since it's going to be mxfp4 native, it'll take ~1.5TB of VRAM to host this, which is juuust at the limit of 8xb200s (but realistically you'll need 16x for context / throughput optimisation). Won't be cheap to host, but at least we should get some range of $/MTok for a 3T model. Then we'll be able to guesstimate if "labs are subsidising tokens on API pricing".
Also interesting to see what effort it will take to fine-tune this beast. The latest AISI benchmarks on cybersec place it above glm5.2, but still way way behind SotA closed models. Some fine-tuning might be needed here. Also, interesting to see if Cursor does another training round on it, to directly compare it w/ kimi2.6/2.7 fine-tunes (composer series) and grok4.5.
Also also, interesting to see if someone takes on distilling (proper distillation, w/ training the entire distribution) from this into smaller models. (dsv4-kimi should be really good, since dsv4 is very cheap to serve)
It will be very interesting to see what kind of 'slow' performance people get from running it on a no GPU, but tons of RAM server (like a dual or quad socket xeon with 1.5 to 3TB of RAM). For the purpose of giving it longer duration tasks to generate a piece of something and come back and check on what it has done in 4 or 6 hours. Even if the output is like 5-6 tok/s, that might be usable for some purposes.
Huge price difference in what you can do with buying a used 4U rackmount server and putting 3TB of RAM in it (64GB DIMMs x quantity 32 in a quad socket xeon, you can see some benchmark prices on eBay for sets of 16 or 32 matched 64GB ECC DIMMs) for <$30,000, vs the cost of trying to run it on real GPU hardware.
Now obviously, as of the time I write this, the full precision hasn't been released nor has anyone like unsloth run it through quantization yet to produce a "Q8" or "Q8-XL" variant of it. But I think it's going to need more than 1536GB of RAM, with a usable and large amount of context, more like 2TB and preferably 2.5 to 3TB.
I also predict that people who try to run it in Q4 and Q6 will get the worst of both worlds, less precision/lost knowledge but also not reliable output that comes out too slow. In my personal opinion if I'm going to deal with something that is smart but slow and running on limited budget hardware, I need it to be Q8.
> Even if the output is like 5-6 tok/s, that might be usable for some purposes.
You'll spend ~100x more on electricity than the API cost to have it run on someone else's GPU at several hundred tokens per second.
I think some sort of extreme data privacy requirement is the only situation that justifies this, but the intersection of {needs absolute data privacy, needs to run SOTA model, cannot afford GPUs} is really really narrow. I wouldn't be surprised if this is an empty set.
There are a number of use cases where sending the contents of your context and prompts (and the resulting output) to a 3rd party service is off the table as an option, and people will compromise speed for data sovereignty. And not everyone's electricity is equally expensive, I pay about $0.075 USD per kWh. It would for example cost me about $48 a month of electricity (not counting cost of cooling) to run a quad socket Dell R940 for a month.
Do I really need to? No, not really. The 27B full density, 35B MoE, 70B and 122B models I have in use get me 95% of the way there on a lot of things. Particularly when dealing with languages and systems where I have at least an intermediate level of knowledge on, to know whether something is going down a dead end, using a wrong method, metaphorically chasing its tail, or is producing valid output.
On the other hand, would it be cool to also have a really big thing as an ancillary tool that I could throw a request into opencode before going to bed, let it crank away and take a look at what it's done 7 hours later? Yeah, particularly if I (very much an unknown quantity at this time) could be confident that it builds high quality, syntax valid, appropriately commented and not absurd code.
As someone who has worked in two industries that are at the maximal end of data sensitivity and privacy this comes across as a tinfoil hat issue not a real business requirement. In such cases we've always found ways to trade dollars for the privacy we need without having to run our own inference at excruciating slow speeds.
Do you mean by trading dollars for the privacy you need as:
a) Contracting with a third-party independent inference provider who will run your choice of model on fast hardware that they own, with all appropriate data security/privacy/contractual/compliance protection in place
or
b) Contracting with the original creators of the model to run inference via their API and with assurances that all the same data protection is in place
or
c) Spending the money to buy your own inference hardware to run it on something you fully own/control at proper usable speeds?
Edit: Everything I've been writing in this thread is mostly within the context of being able to evaluate K3 and its usefulness to be self-hosted as a preliminary proof of concept or test of feasibility of a new thing, such as on <$20,000 of server hardware, before proceeding to spend 300-400k on GPU-related hardware, or external third party services/ongoing billing.
They'll give you HIPAA compliance, they even have a data center for US government classified data, they can give you European data sovereignty. And with OpenAI and Anthropic models to boot, you don't even have to settle for open weights.
What kind of privacy needs do you really have beyond that?
It is not my use case but given recent political developments in international relations caused by the executive branch of the US government, off the top of my head, I could think of a lot of European or Canadian firms for which that would not be an option. No matter what they might promise about European sovereignty. For a good 'ol patriotic US domestic company? Sure.
There are regulated sectors in countries where data sovereignty is important enough that the sector sticks to air-gapped on-prem hardware and does not use cloud services at all. They have the dollars to pay for more than what it would cost to run on the Cloud.
Having worked in / adjacent several such industries, a lot of the question depends on scale.
A trillion-dollar business can easily trade dollars for the privacy. A business with $1M to spend won't even get a phone call with OpenAI or Anthropic, who were the only* previous players in town for doing this.
Worst-case example: Bootstrapped startup working in military.
It's also the case that an open model enables many more intermediate-cost solutions. E.g. providers certified for specific applications, on-prem rentals, etc.
* Omitting Azure, which gives some privacy for some $$$ on their models, but not at the level of high-security.
> Omitting Azure, which gives some privacy for some $$$ on their models, but not at the level of high-security.
If I were ranking third parties on their ability to safely handle my data without compromising it, I would rank Anthropic pretty low for things like Fable (where they more or less promise that they will misuse my data), but I want Azure pretty low in the sense that I fully expect them to be compromised.
I would tend to trust Amazon to avoid being compromised.
I’ve priced it out: max $135/month to run a dual Xeon 2U server with 3T RAM & 2x 22 core Xeon Gold. It’s the 2x 750W power supplies that ultimately determine opex. My power costs $0.124/kWh, the $135 assumes drawing maximum power continuously, and in that case, I can probably offset my heating bill a little bit in the winter, so maybe effectively a little bit lower.
I don’t know if that’s 100x more than I’d pay (opex-wise) with an nvidia setup, but I can say the one-time capex is a great deal cheaper. Avoiding VRAM and DDR5 (fast DDR4 should be OK) are the biggest cost savers. ECC RAM is worth the extra price. General datacenter-quality hardware has less price sensitivity, and plenty of bang for your buck.
Keep in mind that just because it has dual 750W power supplies that doesn't mean it's what its load will be, for a full CPU loaded wattage figure you'd need basically a pair of kill-a-watts plugged in inline on the feed for each poewr supply and then run stress-ng with artificial cpu stress on all cores for an hour.
Under heavy inference load you will find that the cpu usage is actually less as the bottleneck is the RAM bus speed. An older 2U rack server that is 600W load (typically a 1+1 power supply server when plugged into two kill-a-watt would show 300W on each, equal load balancing) when maxed out with stress-ng might be only 450W total running inference.
If you have 600kWh used in a month by running something 24x7 and your power is $0.15 a kWh, that's more like $90/mo (not counting cooling or any ancillary costs for the environment where it's in).
I dunno, K3 thinks a lot before it actually replies, and you might be in the ~1 tok/speed region or even "seconds / tokens", and with K3, you'd wait days if not weeks for a reply in that case.
Don't get me wrong, slow is sometimes better than "not at all", but depending on the performance, it might end up way too slow to even work for batched/async jobs like that.
I agree it's very likely to be painfully slow, I very much want to see some real world results from people who try it. Early testers will inform others on whether it's even worth trying. Results very much TBD right now. I don't have a system sitting around here with 2TB of greater of RAM that isn't already committed for other uses, regretfully.
Lets say an easy response takes 32k tokens in total, and to be generous, let's say it does 1 tok/s. This is already ~9 hours, and 32k reasoning tokens isn't even that much and as mentioned, K3 probably does the longest/most reasoning/thinking out of the available open weights models today, much like GLM. Just lowering that performance to 0.5 tok/s, would lead to ~18 hours for a simple prompt to receive an answer.
And then that's just for single prompts, what about agent harnesses, where before every tool call the model could reason a bunch?
I agree with you that real world results would be interesting, but I wouldn't hold my breath nor expect it to realistically be able to be useful. Still, people should try it, for science if nothing else :)
It's a great concept but I think it would cross the line from 'very slow' to 'so slow it's unusable' at this size. Even if we say you have an NVME SSD that does 7GB/s reads, that's dramatically slower than being able to hold the whole thing in DRAM. Like the difference between 1.3 tok/s in RAM vs 0.1 tok/s with a colibri-like method.
edit: the results I have seen from people trying colibri with fast consumer grade PCI-E 4.0 NVME SSD are 0.1 tok/s on models that are <700B in size, things that are well under 800GB on disk. With something that's 3T in size it'll probably be a lot slower than hat.
For single stream inference of a MoE model, the size of active sparse parameters will matter a lot more than total parameters. This is generally around half of the reported active parameter count - the other half being a dense subset that can be easily cached in VRAM even on fairly modest consumer setups. So the achievable performance may be quite a bit better than a naïve assessment might suggest.
1536GB of DDR4 ECC server RAM is somewhere between $4000-6000 USD used right now, by the time you put in parallel enough NVME SSD to approach good speeds, you'd be approaching that (and also likely running out of PCI-E bus lanes directly attached to the same motherboard to reasonably do so).
Presumably it’s MoE and only needs to read a small fraction of the weights per token. Bonus points if you can get decent speculative decoding without becoming ALU-limited.
The performance bottleneck is not really so much the number of cores or processing power in each core, but the memory bus bandwidth to/from the CPU. I have an older dual socket xeon server here which is a CPU-only LLM test machine with 256GB of RAM and the actual CPU stress is not much, I can even quantify this by how little it spins up the CPU fans to meet thermal load (the CPUs are operating at nowhere near their 180W per socket max capacity, compared to like, crunching prime numbers or running cpuburn).
But the memory bus speed is fully committed when generating tokens or thinking.
Thats where the threadrippers really excelled. They had the lanes for memmory access. We might soon see the return of dinner plate-sized CPUs with thousands of pins.
You're assuming inference providers are going to sell tokens at cost. You're also assuming that the inference providers have will optimized inference engine. I haven't seen that to be the case so far, to be honest.
Take a look at GLM 5 vs GLM 5.2 pricing -- GLM 5.2 cost more despite being the same model.
Take a look a look at DeepSeek, which hosts DS v4, profitably, yet others aren't able or willing to match the price.
Speaking of finetune, currently a common practice is LoRA over bnb 4-bit base model, but I think it's time to replace bnb with GGUF as the base model format. GGUF is actively supporting new model architectures and more aggressive quantizations.
I've made some proof of concept in https://github.com/woct0rdho/transformers5-qwen3.5-recipe . We can finetune Qwen3.5-35B-A3B in 16 GiB VRAM, and DeepSeek-V4-Flash (284B-A13B) in 90 GiB VRAM, without CPU offload. This works well on unified memory machines like Strix Halo.
Even so, larger models like Kimi-K3 still require multiple GPUs and nodes, and there are a lot more to do compare to single-GPU training.
> No, you don't. Without training cost you can infer only the marginal cost of serving this kind of models.
Still useful; "are the labs marginally profitable just on the marginal inference costs?" is still a useful question to answer. After all, if they aren't even profitable on inference in isolation, then we can expect to see large price increases.
If they are able to turn a marginal profit on inference alone, then perhaps the price increases won't be so severe (or perhaps they expand the time between generations so that they spend less on training but take longer to complete training).
"Are the labs profitable at all?" is, of course, a much more useful question, but that doesn't mean that the first question is completely useless.
> If you get close in output quality, then does that matter?
When you're trying to estimate/infer the costs of serving the tokens and even include the cost of training the weights in order to output tokens then yeah, why wouldn't that matter?
Well, or if you're participating in a discussion on HN where the sub-topic happens to be "if labs are subsidising tokens on API pricing" and literally the cost of serving the tokens is relevant to the sub-topic people are trying to discuss...
Training cost is directly impacted by inference cost nowadays. Most of the gains come from RL these days, and that is highly dependant on inference (~7:1 inference:training in units of compute). That's mainly because you want many roll-outs for each training scenario.
Of course inference efficiency is dictated by model architecture, size, etc. You can still guesstimate some of those and have an idea about cost/serve at several size tiers.
I believe they are talking about the closed models' training costs.
I other words, the providers that will be offering K3 inference don't have any training costs to offset, so they are only charging for the inference itself. OAI/Anthropic would need to offset their R&D and training costs in order to not be selling API access at a loss.
Say a single Kimi K3 is deployed on 16 x B200s: how many concurrent users can that handle? I realize the question assumes a major simplification that everyone's prompts/sessions are the same.
Since the model is natively MXFP4, I think it'll be even more interesting on the hardware front. It'll comfortably fit on a 8x AMD MI355X node. I suspect that'll drive token prices down, further.
We have a lossless compression codec (working on open sourcing it over the next couple of weeks) that reduces it down to its minimum entropy -- it cannot be compressed further. On all tested large models, it's a ratio of 1.34-1.23 -- and smaller models up to 3.76x. It also increases the effective bandwidth by the same rate.
If it takes so much resource to run, how does the sharing of a single llm works? There is some interface that basically submits context/cache plus current promt, from each user, doing basically time-sharing compute?
If it is a mixture of experts (MoE) model like the 2.x models, won't this reduce the hardware needed to run the model?
The Kimi-K2.6 model is 1.1T parameters with 32B active parameters. With light quantization (Q6_K) that's enough to run it (slowly) on a single 5090. On a single B200 you can have 5-6 experts loaded into VRAM at a time. Realistically that would be 3-4 to account for the context. [!]
[!] With this and other MoE models it looks like an interesting area for research would be to detect or predict which models would be needed ahead of time. That way you could schedule the load into VRAM step before the weights are needed. That way you shouldn't lose much/any performance from offloading the weights to RAM.
> The Kimi-K2.6 model is 1.1T parameters with 32B active parameters. With light quantization (Q6_K) that's enough to run it (slowly) on a single 5090
Without leveraging system RAM and/or SSDs, I don't think you can, or how exactly are you running this, if this is something you are doing today? With CPU/expert offloading you could probably do it with a 5090 + 1TB of RAM or something like that, but absolutely not on a single 5090 entirely within VRAM.
> There are a lot of optimisations that are not in the public sphere
Sure, but if we're participating in public discussions, isn't it more fun if we talk about things people can actually read and understand, rather than secret stuff other's can say work, but no can actually validate or know how it works?
It sounds like "hybrid approaches are much better than the public is aware, because everything else is private and secret", but also: ok, so what? No one can run that anyways, (yet?), so why it matters?
Alright, I guess I misunderstood. To be fair, this part:
> The Kimi-K2.6 model is 1.1T parameters with 32B active parameters. With light quantization (Q6_K) that's enough to run it (slowly) on a single 5090.
Is painting a very different perspective, even considering the latter parts it's hard to read that as "Of course offloading everything else that doesn't fit on the GPU itself". But anyways, it's been clarified now so no harm :)
I assume you mean putting only the 32B active parameters on the GPU, and the rest on a bunch of regular server DRAM like on a 768GB to 1024GB RAM server?
Because Kimi K2.6 in Q4 is about 584GB GGUF size on disk and will use slightly more than that in RAM, Q8 is 595GB.
You need whole weights in VRAM for optimal performance. Don't be confused by "experts" in the name -- you don't get to load static subset of experts and blast next 100 tokens with them. In typical MoE model they get switched "randomly" on every token, so all experts have to be readily available.
> With light quantization (Q6_K) that's enough to run it (slowly) on a single 5090.
Kimi K2.6 is released as INT4 already.
So 5090 with K2.6 is just gonna sit idle 99% of the time, waiting for next slice of weights to load.
5.6 Sol calculates that single 5090 in raw compute & memory bandwidth can run K2.6 at 35 t/s (256k context depth) -- if it somehow had enough memory to hold whole model in VRAM. Man, I hope HBF succeeds and Nvidia brings it to consumer cards in 5 years..
> In typical MoE model they get switched "randomly" on every token, so all experts have to be readily available.
It's worse than that: a typical MoE model routes a separate set of experts at every layer, not just every token! But in practice, RAM offload (for systems with non-unified VRAM) and even SSD offload still work surprisingly well given some amount of caching.
You can likely recover compute intensity and throughput by batching requests together, which (in practice, depending on sparsity) will end up reusing some of the loaded experts with high probability; though the obvious tradeoff is that having to store KV caches for the wider batches may leave you with less room to cache experts across layers and tokens.
(Plus if you're batching so widely that you end up loading essentially entire model layers, MTP then becomes applicable even for a MoE model. But this typically only applies if you're doing inference on a very large scale, or if your memory bandwidth is so scarce that you have to recover compute intensity by any means feasible.)
You're talking about running this "at home" for 1 user, using a mix of VRAM and RAM (total should be ~1.5TB). That's certainly possible. It'll be slow, especially prompt processing, but doable for single users.
But my comment on running it was more towards serving this profitably at scale. You get much better throughput / unit of compute if you load everything in VRAM and serve many requests at the same time. That's how all inference providers are doing it.
I was talking about running this on a server, hence my comments re 1xB200. Obviously, the more hardware/VRAM you have the better/faster you can run these large models. But if you are a small/medium sized company you could feasibly do it on just one B200. It all depends on how much hardware you can afford to run.
Most likely, since they were acquired. But for us outsiders it would be a cool thing, to see if the delta is the same between kimi2.x + cursor data -> kimi3 + cursor data.
> SemiAnalysis estimates that Anthropic's current blended gross margin has risen to the mid-60% range, with the API business gross margin exceeding 80%
Of course, people will insist "they are lying", "why should we believe them, it's well known they subsidize API pricing", ...
Agreed. My (somewhat educated) guess is that top labs have healthy margins on API pricing. But this release will add another 3rd party / clear of conflict datapoint in this estimation.
Or even the basis of the cost of hardware. There are lease deals, capacity traded for equity, various programs by Nvidia, there's absolutely massive depreciation, etc.
I feel like most hardware to run LLMs on is shaped wrong for individuals.
It's either having a model struggling along with like 5-10 tokens per second on unified memory, or data center cards with hundreds of GB of VRAM consuming more than a kW of power. It doesn't seem like there's prosumer GPUs with like 180W-250W TDP and 128 GB or 256 GB of VRAM (one can dream). Then bifurcation and even just two of those cards would be kinda useful (albeit NVLink or equivalent would need to be commonplace).
Obviously nobody is running Kimi K3 locally without an insanely beefy homelab and lots of money to burn, but running GLM 5.2 would be cool at like ~100 tokens per second for a single session and maybe ~60 tokens per second with N subagents.
I have found that the "mostly didn't lose anything" Q8 large models that I want to run are all too large to run on the "only $3995!" 128GB max RAM systems that some people are buying, and definitely won't fit with any usable amount of context. Things like Qwen 3.5 122B Q8 or deepseek v4 flash Q8, or Laguna S 2.1 Q8 need 170-190GB of RAM including full context, which fits on a 256GB RAM dual socket workstation or rackmount server (sans GPU).
Copy and paste below from my notes and reported memory consumption with latest llama-server, assuming use of "--no-mmap" to load the entire thing into RAM at the time that llama-server launches.
DeepSeek-V4-Flash-UD-Q4_K_XL via unsloth
145GB on disk GGUF
0.03.323.204 I common_params_fit_impl: projected to use 178175 MiB of host memory
DeepSeek-V4-Flash-UD-Q8_K_XL via unsloth
151GB on disk GGUF
0.02.215.885 I common_params_fit_impl: projected to use 184636 MiB of host memory
Laguna-S-2.1-UD-Q8_K_X via unsloth
120GB on disk
0.01.616.119 I common_params_fit_impl: projected to use 172860 MiB of host memory
Qwen3.5-122B-A10B-UD-Q8_K_XL via unsloth
160GB on disk GGUF
165GB RAM use on launch, fresh context
0.04.976.905 I common_params_fit_impl: projected to use 170038 MiB of host memory
There's an emerging practice of using Q4 quants and Q8 KV cache for local inference.
At that point you can run both Qwen3.5-122B-A10B (my personal choice on Framework Desktop 128gb) and Laguna-S-2.1.
Now whether that's good enough for one's use-case remains to be determined. You can also get more out of those (local models and quantizations) if you further tweak the harness you use them with, but tbh this is where it gets too much work (at least for me and the time I have available).
> emerging practice of using Q4 quants and Q8 KV cache for local inference
That's not an emerging practice, it's a tested strategy that is these days only used as a last resort by those desperate to fit a model in memory. Some models do better than others, but generally the model quality suffers greatly under those conditions.
I have never seen anyone report "this produced really great results" from intentionally quantizing their context vs. leaving it at full precision which is the ordinary default.
LLM inference unfortunately also seems to be a task that's poorly formed for moderate consumer hardware,as a single user. For a single user use case, the load is bursty but requires the weights to be in memory already. So a multi user server that keeps the model weights in parts of its memory and then spends some more per user kv cache is wildly more efficient and the wildly expensive gpu cores aren't just sitting idle most of the time. Don't get me wrong, most desktop workloads are bursty, but the power needed to to them has gotten cheap enough that we can have way overkill for idle scenarios hardware just sitting on our desks.
Why does it have to be so bursty though? Just let it run multiple continuous-batched inferences overnight. This would work especially well in combination with SSD offload, and given any kind of sparse attention (common in more recent models) even swapping out the KV cache itself to disk might ultimately be a win. I wouldn't be surprised if something like that ultimately became feasible for single users running even K3 itself.
I find it difficult to always have one or more long-horizon tasks 'queued up' and ready to run... I find myself usually bottlenecked on design, review, or something similar that requires me being in the driver's seat. It's possible I could queue up a bunch of tasks, letting the LLM run off in multiple directions, but then I'd be less able to steer and course correct.
Just my experience though, I'm still figuring things out. Perhaps some subsets of tasks would be more ideal for these long-horizon workloads - exploration, multiple competing implementations, etc...
If your workload fits long batches throughout the night you could schedule them better, yeah. But I think very few have a usage pattern like that?
Given the hardware shortage in the world, I suspect renting ("sharing") via APIs will likely remain cheaper for the foreseeable future since each piece of hardware isn't sitting idle nearly as much.
it has to be so bursty for realtime usecases like chat, which is what most people are using it for today. of course, once (if) stuff like software dark factories start working out for the average person, then you'll be able to make full use of your hardware for workload where asynchonous execution is feasible and have it run several parallel tasks overnight, with an orchestrator managing the gpu(s) allocations.
I've been feeling for a while that as we keep increasing model size, we're going through the opposite of the PC revolution.
The "democratisation" talk from the frontier labs is especially egregious when they only release closed models (gpt-oss hardly counts) and are trying everything they can to make it harder to run open models.
Yeah, I've been experimenting with DiffusionGemma which sadly isn't as smart as Gemma itself, but holy hell is it FAST, and has image input as well, so doing things like "take a screenshot once per second + ask the model to categorize/model it WITH reasoning before" becomes realistic and doable.
I ended up implementing DiffusionGemma myself with Candle in Rust + CUDA, and it's quite literally the fastest model I've managed to run on my hardware.
I agree but worth noting that it's never gonna be very practical to run LLMs like this at home. Unless we have some sort of design breakthrough, the only "sensible" way to run them is at high batch levels on shared HW.
Like, yeah if I could spend a few grand on such a GPU I probably would coz I'm a rich nerd, but I'd acknowledge it as an extremely inefficient luxury, kinda like a sports car.
So I think you could say the real misfortune is that we don't really have the technology (be it computer tech or political/social tech) to do that shared-HW thing in way we can truly trust.
We could make LLM inference 100x cheaper to run at home efficiently, but that solution might need to be updated every 1-2 years, whereas current GPU are useful for various others tasks and last longer
The individual-shaped-hardware problem gets even sharper at the phone end. Shipping a 3B model on-device, the usable RAM budget after the OS and everything else is more like 2-4GBtotal, not per-model so it's not 'can I afford more VRAM', it's 'can I fit a language model and an STT model and embeddings without the OS killing my process'. Feels like phones are the most hardware-constrained 'individual' tier and get the least airtime in these kind of discussion. Is that because the models that fit are still too limited to be interesting, or something else?
Recently spent a few hours messing with bonsai 27B and ternary bonsai 27B at total weights + context fitting in slightly under 6GB RAM, and it's just dumb as hell. It writes what seems like grammatically correct content but it's extremely limited.
It will also happily hallucinate new names and content to fill in gaps in its knowledge, and present the hallucations in what looks like a correctly formatted sentence, so it could fool a person who doesn't know the subject matter. Like, I asked it for a description of Seattle and it hallucinated a name and description of a nonexistant tallest building in the city and suggested the view from its observation deck .
In no way was I surprised, it's asking a lot of under 6GB RAM usage. But I think for 99% of people they will get better results doing something over the network where the weights and inference engine are not on the device.
An AMD R9700 gets 20-50 TPS at ~300 watts on 27B. 100 TPS for the 35B MOE model. And there might be some more optimizations to that as AMD software support gets better with ROCm's latest versions.
The next mac Ultra will allow to run a big model locally with acceptable speed. But we need people to optimize it for that computer, and we’ll be more limited in models we can choose from
128GB is enough to run a large model, quantized, REAPed, with MoE and fast SSD for model weights
GDDR/HBM takes more power, and needs bigger GPUs to be fully utilized. I think the DGX Spark and Strix Halo are the closest you'll get for ~200W and 128GB, and the next Halo should have 192GB.
You're right, and it's interesting to consider why. It's probably a combination of a few factors:
1) Local LLMs are a relatively new phenomenon and hardware takes years. Apple probably lucked into their unified memory architecture being suitable (in terms of memory size and bandwidth) for local LLMs, but it's only with the newest generations we're hearing about LLMs even being a consideration in their design process.
2) NVidia seem to be deliberately blocking consumers from taking this path - as evidenced by the removal of NVLink from the 30x0 series onwards - probably to protect their data center cards from internal competition?
3) Perhaps there's just not the market for it? It's feasible that the number of nerds interested local LLMs is very small in numbers, sales, and profit potential compared to gamers on the one side, and data centers on the other. (This would explain why AMD and Intel aren't trying to out-innovate NVidia in this area, despite it being an obvious opportunity.)
We already know that competition brought GLM 5.2 prices down roughly 45% since its release on June 16th (1.5 months ago), and the price downward slope is probably still going (I've been checking regularly and new providers keep fighting on price, I don't think prices have settled yet). For reference : https://openrouter.ai/z-ai/glm-5.2#providers
I saw arguments like "Providers cannot price less than their costs" in other comments. In economics, it's generally admitted that they shouldn't price less than their marginal costs, i.e. in their case roughly the cost of electricity, since a lot of these datacenters are not at capacity in terms of graphics cards usage (speculation since it's very easy to rent a GC for a couple hours on some providers). My guess is that someone will be selling tokens at less than electricity + depreciation of GCs soon, since there's a lot of competition and "smaller" data centers have overcapacity? This is speculation, correct me if I'm wrong
> My guess is that someone will be selling tokens at less than electricity + depreciation of GCs soon, since there's a lot of competition and "smaller" data centers have overcapacity? This is speculation, correct me if I'm wrong
My guess is they are selling you the tokens, then selling your tokens (data) onto someone else.
I see these conspiratorial arguments all the time and I think people massively overestimate the value of the average users tokens.
The problems with frontier models (design taste, ability to solve novel/difficult problems, etc) cannot be solved by throwing more slop from the average user at it.
Actually, most of the main deficiencies in current models stem from the fact that their data sets aren’t curated and specialized enough.
Press x to doubt on the 45% number. The cheaper providers on open router are fp4 vs fp8 for official zai. There are some cheap fp8 ones (like novita) but the ui makes it seem like it's a temporary promotion, with their normal prices being almost equal to official zai (idk much about open router so not really sure what's going on with these discounts)
I heard this is the talk in town these days. Why can't Meta keep up? With >10000000x more resources you'd think that they'd be able to introduce equally performant if not better open weight models
The cynic in me says maybe they would be further along if they hadn't spent $80 billion on trying to build the "Metaverse" VR world. I've never met anyone who actually uses it and to the best of my knowledge it has very low mass market uptake.
Because lack of talent and organizational disfunction matters a lot more than you think. The reason why OAI and Ant are always at the top is because of this and I’d say compute is third on the list.
I would argue that they actually don’t lack talent, they have an insane bench of really smart people. What they lack is any sort of direction and leadership. They are a ship lost in the ocean and up until now have been lucky to find a few treasures along the their way.
You can make the same argument for closed models. Why spend hundreds of billions training larger and larger models when you can just use Chinese models? Spend that money somewhere else further up the stack where there’s more value. Let China do the training since they’re so efficient at it.
as a big tech company you have the resources to make many bets and do a lot of things at the same time. it's good to have some specialists with knowledge of model training "just in case".
Given the frontier-level capabilities of Kimi K3, I'm wondering if it's possible to extract the core capabilities (fundamental reasoning and tool calling) of the model into a smaller one that consumer devices could run? Not sure exactly how, but either by heavy distillation or some other surgical method since Kimi has a Mixture of Experts architecture.
I think it's very valuable to have a smaller model that doesn't have any domain knowledge or facts built into its weights, but given the right context, could accurately reason about what to do and use the right tools.
I'm aware of colibri [1], but so far I've only seen extremely slow performance.
There’s another way besides distillation that’s way cheaper: You can have the big model build prescriptive skills that the small model follows.
Take the “train” portion of tasks on some benchmark, have K3 complete it, and then output detailed descriptions of tools used and why, then run the validation tasks with some small model that has access to the skills.
"I'd like a car that goes 300mph and gets 100mpg while doing it. I'm aware of a car that gets 100mpg but it is extremely slow."
You are describing fundamental tradeoffs. Getting more performance relative to model size and training token amount is what all of the labs are solving.
Labs are focusing on creating models, small or large, that perform well on various benchmarks, including general knowledge, domain-specific expertise, and agentic capabilities.
Asking for such a model while wanting to be small and fast would align with what you're describing, which I believe is different from what I'm pointing to.
The model I'm describing sacrifices domain knowledge and expertise for agentic reasoning and tool-calling capabilities at a reasonable speed.
This is probably one of the ways to achieve this. I see a plethora of such fine-tunes on HuggingFace [1], but they're either not much different than the base model or they're outright benchmaxxing.
As a completely one person, single sample anecdote, the 'heretic' uncensored Q8 GGUF variants several people have published of Qwen 3.5-122, 3.6-27B and 3.6-35B-A3B will very happily discuss just about any controversial topic that the CCP hates. Including lots of things that would get you thrown into prison if you published them in Mandarin on the domestic Chinese internet.
You could likely further de-censor a model by having a set of 'test' prompts in native Mandarin, Cantonese or really just about any other language. I don't speak any Chinese languages so I don't know if the published 'heretic' GGUF files some people have been throwing around will cooperate, or refuse, if you ask it in Mandarin for how to build a meth lab or precursors for semtex.
Indeed not, but I was saying there's more than ample precedent which is tested/working and actually doesn't refuse anything. Go to the Huggingface 'models' search interface and type in "heretic". Or uncensored. One example would be: https://huggingface.co/HauhauCS/Qwen3.5-122B-A10B-Uncensored...
Yeah, I think we will know more within a couple of days, once people actually download/run/test it. I'm sure the people adjacent to the 'heretic' developers will give it a test as soon as they get their hands on it. All very theoretical right now.
> I think we will know more within a couple of days
It's a 3T parameters model, with a weight format (MXFP4) still not completely integrated into the ecosystem, which only a few has the hardware to even do inference with, much less fine-tuning or more post-training. But sure, do sit and wait a few days :)
It would, indeed, be interesting to compare, given what we know about Anthropic’s censorship and political bias in their closed and more expensive models.
What China (and Japan) uses is YYYY年MM月DD日, which IMO is the superior date format since it's self-explanatory - the sections are spelled out right there!
Jumbling together year, month and day and having to separate them by counting digits is not an improvement for human readability. (And you have the year wrong.) Any of “27 July 2026”, “July 27, 2026” or “2026-07-27” would be superior.
It's good because it's an actual standard instead of 7/27 which is backwards for half the world. Besides, I'm actually from the future and they delayed the model a year, learning from Anthropic that good models are actually about to bring the end of society.
Don't even have to go that far, outside of white-collar jobs and some groups weirdly obsessed with scheduling, most people don't use calendars at all, but their manager/boss/significant-other does that for them :)
Not really. Spain's traditional format is dd/mm/yyyy with slashes. This applies for a good chunk of Europe. Germany/Austria uses dot, I think nordic countries embraced the dash. While you might see more adoption in offical/digital contexts, I just double checked a few popular spanish websites, all slashes.
> For the first time, an open-weights LLM is right at the top.
Hmm, not quite true, I think that honor, for better or worse, goes to OpenAI. When they released GPT2 (or GPT1 for that matter) is was quite literally the SOTA in the ecosystem when it was released.
is there a realistic way to distill 2 consumer hardware friendly models with max ~200B and ~20B? Qwen did it, but would it be possible for 3rd parties (unsloth etc)?
Yeah, why not. Toughest part is running the hardware so you can create the traces for downstream training, but once over that hump, nothing would stop you from doing that no.
I believe they don't do torrents because it gives them a lot more control.
Like they can takedown or update downloads and they can prevent someone from trivially bypassing the license agreements you need to accept for some models.
There's no going back on this. This is putting a very capable intelligence in the hands of the masses. Private companies in the US are aching for Trump's protectionism but it'll do nothing. The hardware needed to run this is ofc prohibitive, but actually putting it out there feels like a 'RSA source code on t-shirt' moment for humanity.
No, luckily private companies in the US are aching for this to NOT be banned. NVIDIA, Microsoft, etc. just released that letter. We’re saved from the trillionaire companies (OpenAI, Anthropic) by the other trillionaire companies acting in self-interest (hosting and hardware).
I think it's shameful that Moonshot isn't providing us with party kits like Microsoft did with the Windows 7 Launch Party kit. How am I supposed to properly celebrate this without fun Kimi-themed quizzes for my guests?
I think the results might be underwhelming - AI providers need to turn a profit and can't subsidize, and they're working off of the commodity hardware everyone does.
I wouldn't be surprised if they started offering potentiall bad quantizations with much reduced capability at lower prices (without telling the users, of course)
I would be surprised, considering that OpenRouter requires disclosing the quantization and shows automatic benchmarks to compare between providers for the same model.
As long as they are transparent about what quant they serve the model and any other optimization they do that also affects performance of inferred tokens.
Strange communists, giving away such an expensive model to the public.
On the other note, can't wait to see 1bit quantisation soon and how it performs in benchmarks, if it performs really well in benchmarks, would be very good news for GPU hosting providers, to offer "Opus 4.5 level model at the cost of Haiku 4.5"
FYI huggingface refers to the alien from the Aliens movies that we need to prevent from reaching earth at any cost because it means the end of civilization.
Just checking in because y'all sound good with that.
Also interesting to see what effort it will take to fine-tune this beast. The latest AISI benchmarks on cybersec place it above glm5.2, but still way way behind SotA closed models. Some fine-tuning might be needed here. Also, interesting to see if Cursor does another training round on it, to directly compare it w/ kimi2.6/2.7 fine-tunes (composer series) and grok4.5.
Also also, interesting to see if someone takes on distilling (proper distillation, w/ training the entire distribution) from this into smaller models. (dsv4-kimi should be really good, since dsv4 is very cheap to serve)
Huge price difference in what you can do with buying a used 4U rackmount server and putting 3TB of RAM in it (64GB DIMMs x quantity 32 in a quad socket xeon, you can see some benchmark prices on eBay for sets of 16 or 32 matched 64GB ECC DIMMs) for <$30,000, vs the cost of trying to run it on real GPU hardware.
Now obviously, as of the time I write this, the full precision hasn't been released nor has anyone like unsloth run it through quantization yet to produce a "Q8" or "Q8-XL" variant of it. But I think it's going to need more than 1536GB of RAM, with a usable and large amount of context, more like 2TB and preferably 2.5 to 3TB.
I also predict that people who try to run it in Q4 and Q6 will get the worst of both worlds, less precision/lost knowledge but also not reliable output that comes out too slow. In my personal opinion if I'm going to deal with something that is smart but slow and running on limited budget hardware, I need it to be Q8.
You'll spend ~100x more on electricity than the API cost to have it run on someone else's GPU at several hundred tokens per second.
I think some sort of extreme data privacy requirement is the only situation that justifies this, but the intersection of {needs absolute data privacy, needs to run SOTA model, cannot afford GPUs} is really really narrow. I wouldn't be surprised if this is an empty set.
Do you actually need to run the state of art model at 5 tokens per second instead of a qwen or whatever 7b or 30b model at 100 tokens per second?
On the other hand, would it be cool to also have a really big thing as an ancillary tool that I could throw a request into opencode before going to bed, let it crank away and take a look at what it's done 7 hours later? Yeah, particularly if I (very much an unknown quantity at this time) could be confident that it builds high quality, syntax valid, appropriately commented and not absurd code.
a) Contracting with a third-party independent inference provider who will run your choice of model on fast hardware that they own, with all appropriate data security/privacy/contractual/compliance protection in place
or
b) Contracting with the original creators of the model to run inference via their API and with assurances that all the same data protection is in place
or
c) Spending the money to buy your own inference hardware to run it on something you fully own/control at proper usable speeds?
Edit: Everything I've been writing in this thread is mostly within the context of being able to evaluate K3 and its usefulness to be self-hosted as a preliminary proof of concept or test of feasibility of a new thing, such as on <$20,000 of server hardware, before proceeding to spend 300-400k on GPU-related hardware, or external third party services/ongoing billing.
They'll give you HIPAA compliance, they even have a data center for US government classified data, they can give you European data sovereignty. And with OpenAI and Anthropic models to boot, you don't even have to settle for open weights.
What kind of privacy needs do you really have beyond that?
A trillion-dollar business can easily trade dollars for the privacy. A business with $1M to spend won't even get a phone call with OpenAI or Anthropic, who were the only* previous players in town for doing this.
Worst-case example: Bootstrapped startup working in military.
It's also the case that an open model enables many more intermediate-cost solutions. E.g. providers certified for specific applications, on-prem rentals, etc.
* Omitting Azure, which gives some privacy for some $$$ on their models, but not at the level of high-security.
If I were ranking third parties on their ability to safely handle my data without compromising it, I would rank Anthropic pretty low for things like Fable (where they more or less promise that they will misuse my data), but I want Azure pretty low in the sense that I fully expect them to be compromised.
I would tend to trust Amazon to avoid being compromised.
I don’t know if that’s 100x more than I’d pay (opex-wise) with an nvidia setup, but I can say the one-time capex is a great deal cheaper. Avoiding VRAM and DDR5 (fast DDR4 should be OK) are the biggest cost savers. ECC RAM is worth the extra price. General datacenter-quality hardware has less price sensitivity, and plenty of bang for your buck.
Under heavy inference load you will find that the cpu usage is actually less as the bottleneck is the RAM bus speed. An older 2U rack server that is 600W load (typically a 1+1 power supply server when plugged into two kill-a-watt would show 300W on each, equal load balancing) when maxed out with stress-ng might be only 450W total running inference.
If you have 600kWh used in a month by running something 24x7 and your power is $0.15 a kWh, that's more like $90/mo (not counting cooling or any ancillary costs for the environment where it's in).
Where in the world are you finding that much RAM in a racked server for $200/month?
Don't get me wrong, slow is sometimes better than "not at all", but depending on the performance, it might end up way too slow to even work for batched/async jobs like that.
And then that's just for single prompts, what about agent harnesses, where before every tool call the model could reason a bunch?
I agree with you that real world results would be interesting, but I wouldn't hold my breath nor expect it to realistically be able to be useful. Still, people should try it, for science if nothing else :)
The model is known to be MXFP4 according to Kimi's release blog post, so the model weights will be less than 1536GB: https://www.kimi.com/blog/kimi-k3
Also, their previous models were native INT4, so it would be weird if they went larger now.
Or from SSD using something like Colibri[1]. Not going to be quick, but at least runable.
[1]: https://github.com/JustVugg/colibri
edit: the results I have seen from people trying colibri with fast consumer grade PCI-E 4.0 NVME SSD are 0.1 tok/s on models that are <700B in size, things that are well under 800GB on disk. With something that's 3T in size it'll probably be a lot slower than hat.
But still fun you can run it at home.
On a 3T model I’d imagine you’d be closer to 0.05 tks
But the memory bus speed is fully committed when generating tokens or thinking.
Take a look at GLM 5 vs GLM 5.2 pricing -- GLM 5.2 cost more despite being the same model.
Take a look a look at DeepSeek, which hosts DS v4, profitably, yet others aren't able or willing to match the price.
I've made some proof of concept in https://github.com/woct0rdho/transformers5-qwen3.5-recipe . We can finetune Qwen3.5-35B-A3B in 16 GiB VRAM, and DeepSeek-V4-Flash (284B-A13B) in 90 GiB VRAM, without CPU offload. This works well on unified memory machines like Strix Halo.
Even so, larger models like Kimi-K3 still require multiple GPUs and nodes, and there are a lot more to do compare to single-GPU training.
No, you don't. Without training cost you can infer only the marginal cost of serving this kind of models.
Moreover, you don't know the actual size of closed models (what if Fable is a 10T model? What if it's 1T?)
Still useful; "are the labs marginally profitable just on the marginal inference costs?" is still a useful question to answer. After all, if they aren't even profitable on inference in isolation, then we can expect to see large price increases.
If they are able to turn a marginal profit on inference alone, then perhaps the price increases won't be so severe (or perhaps they expand the time between generations so that they spend less on training but take longer to complete training).
"Are the labs profitable at all?" is, of course, a much more useful question, but that doesn't mean that the first question is completely useless.
Which is by far the most interesting number of the two.
> Moreover, you don't know the actual size of closed models (what if Fable is a 10T model? What if it's 1T?)
If you get close in output quality, then does that matter?
When you're trying to estimate/infer the costs of serving the tokens and even include the cost of training the weights in order to output tokens then yeah, why wouldn't that matter?
Only if you don't have to continuously train new models, and you are not at a runway risk.
Of course inference efficiency is dictated by model architecture, size, etc. You can still guesstimate some of those and have an idea about cost/serve at several size tiers.
I guess this is one of the reason Anthropic i so "active" for asking for a development break.
Are you talking about Kimi's training cost or the training cost of the model(s) that Kimi distilled?
Because Moonshot didn't even incur the majority of the training costs either
I other words, the providers that will be offering K3 inference don't have any training costs to offset, so they are only charging for the inference itself. OAI/Anthropic would need to offset their R&D and training costs in order to not be selling API access at a loss.
> reduces it down to its minimum entropy -- it cannot be compressed further.
I think you could make a lot more money elsewhere :-)
https://en.wikipedia.org/wiki/Kolmogorov_complexity#Formal_p...
The Kimi-K2.6 model is 1.1T parameters with 32B active parameters. With light quantization (Q6_K) that's enough to run it (slowly) on a single 5090. On a single B200 you can have 5-6 experts loaded into VRAM at a time. Realistically that would be 3-4 to account for the context. [!]
[!] With this and other MoE models it looks like an interesting area for research would be to detect or predict which models would be needed ahead of time. That way you could schedule the load into VRAM step before the weights are needed. That way you shouldn't lose much/any performance from offloading the weights to RAM.
Without leveraging system RAM and/or SSDs, I don't think you can, or how exactly are you running this, if this is something you are doing today? With CPU/expert offloading you could probably do it with a 5090 + 1TB of RAM or something like that, but absolutely not on a single 5090 entirely within VRAM.
There are a lot of optimisations that are not in the public sphere, source working on start up in this space
Sure, but if we're participating in public discussions, isn't it more fun if we talk about things people can actually read and understand, rather than secret stuff other's can say work, but no can actually validate or know how it works?
It sounds like "hybrid approaches are much better than the public is aware, because everything else is private and secret", but also: ok, so what? No one can run that anyways, (yet?), so why it matters?
> The Kimi-K2.6 model is 1.1T parameters with 32B active parameters. With light quantization (Q6_K) that's enough to run it (slowly) on a single 5090.
Is painting a very different perspective, even considering the latter parts it's hard to read that as "Of course offloading everything else that doesn't fit on the GPU itself". But anyways, it's been clarified now so no harm :)
Because Kimi K2.6 in Q4 is about 584GB GGUF size on disk and will use slightly more than that in RAM, Q8 is 595GB.
https://huggingface.co/unsloth/Kimi-K2.6-GGUF
> With light quantization (Q6_K) that's enough to run it (slowly) on a single 5090. Kimi K2.6 is released as INT4 already.
So 5090 with K2.6 is just gonna sit idle 99% of the time, waiting for next slice of weights to load.
5.6 Sol calculates that single 5090 in raw compute & memory bandwidth can run K2.6 at 35 t/s (256k context depth) -- if it somehow had enough memory to hold whole model in VRAM. Man, I hope HBF succeeds and Nvidia brings it to consumer cards in 5 years..
It's worse than that: a typical MoE model routes a separate set of experts at every layer, not just every token! But in practice, RAM offload (for systems with non-unified VRAM) and even SSD offload still work surprisingly well given some amount of caching.
You can likely recover compute intensity and throughput by batching requests together, which (in practice, depending on sparsity) will end up reusing some of the loaded experts with high probability; though the obvious tradeoff is that having to store KV caches for the wider batches may leave you with less room to cache experts across layers and tokens.
(Plus if you're batching so widely that you end up loading essentially entire model layers, MTP then becomes applicable even for a MoE model. But this typically only applies if you're doing inference on a very large scale, or if your memory bandwidth is so scarce that you have to recover compute intensity by any means feasible.)
But my comment on running it was more towards serving this profitably at scale. You get much better throughput / unit of compute if you load everything in VRAM and serve many requests at the same time. That's how all inference providers are doing it.
they noted in their blog post they didn't focus purely on coding for grok 4.5.
> SemiAnalysis estimates that Anthropic's current blended gross margin has risen to the mid-60% range, with the API business gross margin exceeding 80%
Of course, people will insist "they are lying", "why should we believe them, it's well known they subsidize API pricing", ...
https://newsletter.semianalysis.com/p/anthropic-3q26-profit-...
https://finance.biggo.com/news/02d45650-b569-4d12-b44d-8d6d8...
It's either having a model struggling along with like 5-10 tokens per second on unified memory, or data center cards with hundreds of GB of VRAM consuming more than a kW of power. It doesn't seem like there's prosumer GPUs with like 180W-250W TDP and 128 GB or 256 GB of VRAM (one can dream). Then bifurcation and even just two of those cards would be kinda useful (albeit NVLink or equivalent would need to be commonplace).
Obviously nobody is running Kimi K3 locally without an insanely beefy homelab and lots of money to burn, but running GLM 5.2 would be cool at like ~100 tokens per second for a single session and maybe ~60 tokens per second with N subagents.
How unfortunate.
Copy and paste below from my notes and reported memory consumption with latest llama-server, assuming use of "--no-mmap" to load the entire thing into RAM at the time that llama-server launches.
DeepSeek-V4-Flash-UD-Q4_K_XL via unsloth 145GB on disk GGUF 0.03.323.204 I common_params_fit_impl: projected to use 178175 MiB of host memory
DeepSeek-V4-Flash-UD-Q8_K_XL via unsloth 151GB on disk GGUF 0.02.215.885 I common_params_fit_impl: projected to use 184636 MiB of host memory
Laguna-S-2.1-UD-Q8_K_X via unsloth 120GB on disk 0.01.616.119 I common_params_fit_impl: projected to use 172860 MiB of host memory
Qwen3.5-122B-A10B-UD-Q8_K_XL via unsloth 160GB on disk GGUF 165GB RAM use on launch, fresh context 0.04.976.905 I common_params_fit_impl: projected to use 170038 MiB of host memory
But not every framework implements it properly yet.
0.07.015.888 I common_memory_breakdown_print: | - Host | 170038 = 162913 + 6740 + 384 |
The 6740 is the cache size.
Now whether that's good enough for one's use-case remains to be determined. You can also get more out of those (local models and quantizations) if you further tweak the harness you use them with, but tbh this is where it gets too much work (at least for me and the time I have available).
That's not an emerging practice, it's a tested strategy that is these days only used as a last resort by those desperate to fit a model in memory. Some models do better than others, but generally the model quality suffers greatly under those conditions.
Just my experience though, I'm still figuring things out. Perhaps some subsets of tasks would be more ideal for these long-horizon workloads - exploration, multiple competing implementations, etc...
Given the hardware shortage in the world, I suspect renting ("sharing") via APIs will likely remain cheaper for the foreseeable future since each piece of hardware isn't sitting idle nearly as much.
The "democratisation" talk from the frontier labs is especially egregious when they only release closed models (gpt-oss hardly counts) and are trying everything they can to make it harder to run open models.
I ended up implementing DiffusionGemma myself with Candle in Rust + CUDA, and it's quite literally the fastest model I've managed to run on my hardware.
Like, yeah if I could spend a few grand on such a GPU I probably would coz I'm a rich nerd, but I'd acknowledge it as an extremely inefficient luxury, kinda like a sports car.
So I think you could say the real misfortune is that we don't really have the technology (be it computer tech or political/social tech) to do that shared-HW thing in way we can truly trust.
> April 2016, 8 GB was standard across the 13-inch MacBook Air range
... Now it's 16.
Rich nerds will have quite a bit more. But I suspect the standard of model rich nerds want to use will have gone up somewhat too.
Of course, by then we’ll want to run something commensurately larger.
It will also happily hallucinate new names and content to fill in gaps in its knowledge, and present the hallucations in what looks like a correctly formatted sentence, so it could fool a person who doesn't know the subject matter. Like, I asked it for a description of Seattle and it hallucinated a name and description of a nonexistant tallest building in the city and suggested the view from its observation deck .
https://prismml.com/news/bonsai-27b
https://huggingface.co/prism-ml/Ternary-Bonsai-27B-gguf
In no way was I surprised, it's asking a lot of under 6GB RAM usage. But I think for 99% of people they will get better results doing something over the network where the weights and inference engine are not on the device.
Your power consumption estimates are off for this generation of GPUs. A 27B dense model gets 50-80 tps on an RTX 6000 using 600 watts.
128GB is enough to run a large model, quantized, REAPed, with MoE and fast SSD for model weights
1) Local LLMs are a relatively new phenomenon and hardware takes years. Apple probably lucked into their unified memory architecture being suitable (in terms of memory size and bandwidth) for local LLMs, but it's only with the newest generations we're hearing about LLMs even being a consideration in their design process.
2) NVidia seem to be deliberately blocking consumers from taking this path - as evidenced by the removal of NVLink from the 30x0 series onwards - probably to protect their data center cards from internal competition?
3) Perhaps there's just not the market for it? It's feasible that the number of nerds interested local LLMs is very small in numbers, sales, and profit potential compared to gamers on the one side, and data centers on the other. (This would explain why AMD and Intel aren't trying to out-innovate NVidia in this area, despite it being an obvious opportunity.)
I saw arguments like "Providers cannot price less than their costs" in other comments. In economics, it's generally admitted that they shouldn't price less than their marginal costs, i.e. in their case roughly the cost of electricity, since a lot of these datacenters are not at capacity in terms of graphics cards usage (speculation since it's very easy to rent a GC for a couple hours on some providers). My guess is that someone will be selling tokens at less than electricity + depreciation of GCs soon, since there's a lot of competition and "smaller" data centers have overcapacity? This is speculation, correct me if I'm wrong
My guess is they are selling you the tokens, then selling your tokens (data) onto someone else.
The problems with frontier models (design taste, ability to solve novel/difficult problems, etc) cannot be solved by throwing more slop from the average user at it.
Actually, most of the main deficiencies in current models stem from the fact that their data sets aren’t curated and specialized enough.
Then there's 43% off at StreamLake with FP8 precision and 1M context window.
https://finance.yahoo.com/sectors/technology/articles/mark-z...
Not exactly the best use of dollars and the labor hours of some of the best minds of our generation.
I think it's very valuable to have a smaller model that doesn't have any domain knowledge or facts built into its weights, but given the right context, could accurately reason about what to do and use the right tools.
I'm aware of colibri [1], but so far I've only seen extremely slow performance.
[1] https://github.com/JustVugg/colibri
Take the “train” portion of tasks on some benchmark, have K3 complete it, and then output detailed descriptions of tools used and why, then run the validation tasks with some small model that has access to the skills.
You are describing fundamental tradeoffs. Getting more performance relative to model size and training token amount is what all of the labs are solving.
Asking for such a model while wanting to be small and fast would align with what you're describing, which I believe is different from what I'm pointing to.
The model I'm describing sacrifices domain knowledge and expertise for agentic reasoning and tool-calling capabilities at a reasonable speed.
Think of Cactus Compute's Needle [1].
[1] https://cactuscompute.com/blog/needle
I’ve had success adapting even a 7B model for single-domain tasks that way, including reasoning and tool calling.
You can use an open model. The point is just to outsource the inference, so you don’t have to deal with running the larger model yourself.
[1] https://huggingface.co/models
https://github.com/p-e-w/heretic
As a side note on this, if you see the reference in the screenshot in the link above to the harmful behaviors prompt set, these are all in English:
https://huggingface.co/datasets/mlabonne/harmful_behaviors
You could likely further de-censor a model by having a set of 'test' prompts in native Mandarin, Cantonese or really just about any other language. I don't speak any Chinese languages so I don't know if the published 'heretic' GGUF files some people have been throwing around will cooperate, or refuse, if you ask it in Mandarin for how to build a meth lab or precursors for semtex.
It's a 3T parameters model, with a weight format (MXFP4) still not completely integrated into the ecosystem, which only a few has the hardware to even do inference with, much less fine-tuning or more post-training. But sure, do sit and wait a few days :)
https://x.com/dhh/status/2081435006770249831 (from the creator of Ruby on Rails).
In his specific case Kimi did the task it was asked to do (translation of the article DHH wrote), which Claude refused to.
You can still try it at https://chatjimmy.ai/, but it's running the rather outdated Llama 3.1 8B
Raw fucking intelligence at your disposal, free to download.
If you'd describe what's happening now to someone from five years ago they'd think you're hallucinating or mad.
signed: a hungarian :)
The separator is often the only way to distinguish American notation from ISO, so please use a dash for dd-mm-yy and a forward slash for mm/dd/yy
There are quite some countries around the world using d/m/y
https://en.wikipedia.org/wiki/List_of_date_formats_by_countr...
Algeria, Belgium, Brazil, Chile...
We won't be able to run this ourselves, but many providers can.
Hmm, not quite true, I think that honor, for better or worse, goes to OpenAI. When they released GPT2 (or GPT1 for that matter) is was quite literally the SOTA in the ecosystem when it was released.
Linux distributions got this right: Offer both HTTP and Torrents. Let the user decide.
Like they can takedown or update downloads and they can prevent someone from trivially bypassing the license agreements you need to accept for some models.
Perhaps that's exactly what they're trying to avoid, giving the user any form of control and having them depend on HF.
I wouldn't be surprised if they started offering potentiall bad quantizations with much reduced capability at lower prices (without telling the users, of course)
Other than that they track Tool call error rate and Structured output error rate.
I only discovered this today, and it seems like a good idea. What are the problems in practice?
Now the US government has 5 hours left to (attempt to) stop the release. (and save Anthropic)
Let competition run its course and the market (not government) determine the winners and losers.
On the other note, can't wait to see 1bit quantisation soon and how it performs in benchmarks, if it performs really well in benchmarks, would be very good news for GPU hosting providers, to offer "Opus 4.5 level model at the cost of Haiku 4.5"
Just checking in because y'all sound good with that.