Probably won't have to wait that long. Prism released Bonsai 27B (https://huggingface.co/prism-ml/Ternary-Bonsai-27B-mlx-2bit) as a ternary model a few days ago, its just ~7GB and runs at 44+ t/sec on an m4 max laptop. That's already in the ballpark of active parameter count of most 200B+ models, so we will get a model like this whenever Prism feels like releasing one.
It is debatable if we will actually need that many parameters though, since recursive nets like HRM (https://huggingface.co/sapientinc/HRM-Text-1B) don't need to parametrize as heavily.
agreed!! in my heart i really wanted to say by the end of 2026 but wanted to add some wiggle room in case they start to ban open source AI development.
I mostly agree with the prediction though maybe a bit more pessimistic about the timeline. Also I'm not sure our current usage of parameter count would make sense in this scenario, such a feat would require compressing current parameters in a manner much different then something producing a bit count per parameter. A hypothetical example would be using a single seed parameter per layer which then passed into a noise function produces the functional weights for that layer, able to reduce per weight size to sub bit levels (256 bit seed, producing 16K weights).
But you said 7-9 tokens/second, that's not a decent speed. I'm not an expert by all means but in my local experiments, less than 12 to 16 tps is too slow.
You think of an idea that you want to have the LLM process, queue it up, and go back to what you were doing. Once you've finished reading the next article on HN about a 5 tps Xeon, your task will be complete. It's kind of like using a 3D printer: It doesn't matter if a print takes 10 hours, because when you come back in the morning it will be done.
Yes, with top-tier GPU farms you can hit hundreds of tokens per second. But if the old Xeon in the closet can get useful work done at 5 tokens per second, there are lots of people and lots of use cases where a free, unlimited 5 TPS stream is worth more than paying a dollars per day to get access to a 500 TPS source.
> Once you've finished reading the next article on HN about a 5 tps Xeon, your task will be complete.
If I spend 10 minutes reading an article, that would only generate 3000 tokens.
That’s not counting the prompt processing time.
We have very different expectations for LLMs if your tasks only take a couple thousand tokens and you’re happy waiting 10 minutes for it.
> Yes, with top-tier GPU farms you can hit hundreds of tokens per second
My 5090 gets hundreds of tokens per second with this model. No farm needed. I’d have to double check but I think even a $1000 Intel B70 might break 100 tokens per second.
> But if the old Xeon in the closet can get useful work done at 5 tokens per second, there are lots of people and lots of use cases where a free, unlimited 5 TPS stream is worth more than paying a dollars per day to get access to a 500 TPS source.
If that old Xeon pulls 200W from the wall and you pay national average electricity costs, it’s going to cost $0.90 per day to run it.
I would rather pay a dollar per day, get my answers 100X faster, and not have an old Xeon heating up my house.
Once you've used a model that runs at hundreds of TPS, it's hard to go back. Everything completes so quickly that you can iterate without breaking out of flow state. My biggest gripe with slow (<50tps) LLMs is that I've lost all the mental context I built up by the time it's done, which makes it extremely difficult to explore or iterate on solutions.
It's still the same thing, you can ask it to do a full on report give explanation and details be thorough and then go do something else, another task a lunch break whatever and it will be done when you're back
For me, at least for agentic use, you need at least ~40tps. Less might be good only for tasks you could run in the background (like at night maybe).
Instead of coding agents like tool for local models I would like to see more "docker ps" like tools where you can queue up tasks that get processes incrementally (maybe when the pc i idle) and are specialized for doing retries and caching as much work as possible to work decently with slow local models.
Yep, and we don't even know how long they spent on prefill. A typical 50-100k token session could take 10-20 minutes to prefill on a Mac.
Pending any new hardware or radically different LLM architectures, we're going to be waiting a lot longer than 2027 for 200B models on local hardware. SOC platforms like Apple Silicon are hamstrung by their obsession over raster performance, the hardware lacks the fundamental GPGPU hardware to be a replacement for real-world inference.
> I have a prediction. By the mid of 2027, we will have >200B MoE models running on basic consumer hardware.
This prediction alone isn’t useful at all without a bound on speed and maybe quantization.
You can already run >200B MoE models on basic consumer hardware by picking a low bpw quantization and then streaming the experts from SSD. There have been a lot of proof of concept demos, but nobody uses them because they’re so slow and the quality is so degraded.
If you’re saying that hardware will catch up by mid-2027, I disagree. The limitation is fast memory and that’s going to be expensive for a while. I have a 128GB unified memory machine that can technically run 200B MoE models with enough quantization, but it’s so slow that there’s no reason to do it. It’s going to be a few years before we have enough RAM and processing power in basic consumer hardware without spending as much as a used car to get it.
> This is a GPT4 level model running locally with a decent speed on a 16gb ram macbook air.
Sorry, but 9 tokens per second with a slow prompt processing speed is not decent for anything other than getting short chat responses.
You’re also not running the full GPT4 quality model. I’m very familiar with that model from some other work and the 4-bit quants are just not as good as all of those KL divergence plots would have you believe.
You also have very short context. It’s basically useless for anything more than short chats where you’re okay watching the output come back at reading speed, skipping the reasoning part (which is important for calling it GPT4 level quality), and waiting a long time for the first token.
Yes, it’s technically running, but not in a way that would be useful by normal LLM standards.
i have been optimizing for that. for now samosa is capped at using half of the avaiable cores and switching between them, which keeps the system 'less hot' as it would have been. i will also release better thermal control in the next release. at this point its basically sacrificing about 20% of the speed to keep the hardware less stressed (and hot).
>>It's quite telling you didn't use Qwen3.6-35B-A3B locally to build that
that would have run into a race condition unfortunately ;)
but there is a sample landing page + a python function on the repo which shows what the model produced. my goal is to integrate the local model in my workflow so that claude/OAI can call this model for basic stuff.
I tried Qwen3.6-35B-A3B, but it couldn't generate a 50-100 line Clojure file without having broken parens mismatches. I know Clojure isn't super popular, but the syntax is pretty simple and the frontier models do fine with it.
Some ppl don't like to hear it. But I would assume that token costs when using an inference provider are cheaper than electricity of using locally.
If we just take into account output token generation for simplicity. With 5tps u get 180k tokens an hour. That would costs around 0.05USD from an inference provider.
I estimate that the server consumes probably around 500W during inference.
In Germany where 1kwh cost around 0.3USD, 180k tokens inferred locally would therefore cost 0.15USD which is 3x the costs of using an inference provider.
But for ppl who worry about their data, running locally might still be good. However, they should be aware, that it is much less efficient than using an inference provider.
The efficiency gap will also significantly increase as new GPUs will make inference much more efficient.
I don't pay anywhere near 0.30usd in the US - I pay half that off peak and can buy 1000$ worth of batteries to load up on super off peak (0.11usd). Also the inference providers are fighting over market share with huge debt loads so they are definitely going to go up in price.
It's all relative. On the opposite coast, Maine it is ~ $0.28 cents kwh including getting it there. (~ 50% energy, 50% delivery). It's too darn expensive here.
Of course efficiency matters, but a lot of people either have cheap electricity or efficient hardware. My AMD strix halo home server can serve Gemma4-26B at like 70 TPS (rough estimate, I don’t remember the exact speed buts its fast af) while only using 100W.
It's the "Race-to-Idle" situation all over again. It consumes less power to complete a task faster, whereas using "low power" hardware that draws max TDP for 30 minutes isn't very power efficient.
The privacy nuts have a better leg to stand on, but even then it's hard to believe that they're using on-prem AI to replace SOTA model inference. As cool as local LLMs are, a lot of the stuff people run is a novelty.
Have you tried with a single CPU to get rid of the NUMA penalty? I understand this likely means halving the memory but I am interested in how much of a difference it makes
I have (192GB machine with two CPUs), pretty much does the trick. It just runs some small models used for embedding, etc. and has those on one CPU / memory node and all the Docker containers on the other one.c
I have a dual xeon also, same as OP: Ivy Bridge + 128GB DRAM, and was never really able to get decent LLM performance out of it. So I ended up biting the bullet and adding a "budget tier" A4000 20GB GPU. Too bad all my DRAM is wasted now--not sure if there is a way to take advantage of lots of DRAM once you move over to having inference happening on the GPU.
I run the same setup Gemma 4 26B on a 2013 Mac Pro (dual graphics cards but they're useless for this). I also get about 5 t/s. It's perfectly serviceable for some tasks!
The transformer architecture is fundamentally unsuitable for local inference, while being efficient at scale. It's a fun experiment to try, but that's about it.
Is it just me or does this post not mention how much RAM they had? I would love to know - I have a dual-Xeon 1U screamer with 96GB of DDR4 RDIMM just sitting around...
FWIW I'm getting a hardware max of 20 tok/s (approx topping out the GPU's compute) on my custom local diffusiongemma port running on an M3.
Such a system is RAM bandwidth limited and not compute limited Switching to q4 from q8 would decrease the amount of data needing to be loaded by half. The token generation rate would nearly double. But generally if you can do q6 or q8 and you have enough RAM you really should. Even if it's slower.
To me context means everything.
Tokens per second is a great metric but in the real world context window is the deal breaker when a real use case is on the table.
Author here. The short version: a viral post ran Gemma 4 on a 2016 Xeon; my Xeons are 2013, and the fork it used assumes AVX2, which Ivy Bridge doesn't have. The build failure was easy. The fun bug was the silent one: two MoE graph ops with no dispatch case on non-AVX2 builds, so every expert FFN output was uninitialized memory. Deterministic, NaN-free, fluent-looking multilingual gibberish.
The fix is open upstream as PR #2138 (https://github.com/ikawrakow/ik_llama.cpp/pull/2138), awaiting review. Fair warning on the AI angle: the patch was written by Claude at my direction. The post is explicit about which parts were me and which weren't. Happy to answer questions about either the bug or the workflow.
Here's the thing: life also imitates art. If you invert your load-bearing assumption, it could be that he just reads too much slop. But my honest take? You might be right.
Apologies for asking here but literally nobody knows:
Android studio connected to a local model disconnects automatically after 10 minutes. How set this limit to 12 hours or remove it completely?
I could run my LM studio model all night... but I cant, since Android studio times out after a hard limit of 10M.
This is not related to number of tokens.
I tried Googling, searching for settings in Android studio, even created a stackoverflow post - but zero information. Jetbrains mentions "remote agent timeout mechanism" - but after changing it, nothing happens.
If the local model is served via ollama, there's a default timeout of 10 minutes , which can be adjusted either per-call , or (as I did) in the systemd service environment variables
Thank you for your reply. I use LM studio (local server), but can switch to a different tool.
Do you know how to switch it in LM studio?
What I see is that: android studio gives "Error: stream failed" and in LM studio server I see it is still working, then says that client (=android studio) disconnected.
I am running Qwen3.6-35B-A3B locally on my 16GB mac with 7-9 tokens/second. Link - https://github.com/deepanwadhwa/samosa-chat
This is a GPT4 level model running locally with a decent speed on a 16gb ram macbook air.
It is debatable if we will actually need that many parameters though, since recursive nets like HRM (https://huggingface.co/sapientinc/HRM-Text-1B) don't need to parametrize as heavily.
But you said 7-9 tokens/second, that's not a decent speed. I'm not an expert by all means but in my local experiments, less than 12 to 16 tps is too slow.
https://mikeveerman.github.io/tokenspeed/?rate=10&mode=text
You think of an idea that you want to have the LLM process, queue it up, and go back to what you were doing. Once you've finished reading the next article on HN about a 5 tps Xeon, your task will be complete. It's kind of like using a 3D printer: It doesn't matter if a print takes 10 hours, because when you come back in the morning it will be done.
Yes, with top-tier GPU farms you can hit hundreds of tokens per second. But if the old Xeon in the closet can get useful work done at 5 tokens per second, there are lots of people and lots of use cases where a free, unlimited 5 TPS stream is worth more than paying a dollars per day to get access to a 500 TPS source.
If I spend 10 minutes reading an article, that would only generate 3000 tokens.
That’s not counting the prompt processing time.
We have very different expectations for LLMs if your tasks only take a couple thousand tokens and you’re happy waiting 10 minutes for it.
> Yes, with top-tier GPU farms you can hit hundreds of tokens per second
My 5090 gets hundreds of tokens per second with this model. No farm needed. I’d have to double check but I think even a $1000 Intel B70 might break 100 tokens per second.
> But if the old Xeon in the closet can get useful work done at 5 tokens per second, there are lots of people and lots of use cases where a free, unlimited 5 TPS stream is worth more than paying a dollars per day to get access to a 500 TPS source.
If that old Xeon pulls 200W from the wall and you pay national average electricity costs, it’s going to cost $0.90 per day to run it.
I would rather pay a dollar per day, get my answers 100X faster, and not have an old Xeon heating up my house.
Instead of coding agents like tool for local models I would like to see more "docker ps" like tools where you can queue up tasks that get processes incrementally (maybe when the pc i idle) and are specialized for doing retries and caching as much work as possible to work decently with slow local models.
It says so right in the readme. They’re not hiding anything.
Pending any new hardware or radically different LLM architectures, we're going to be waiting a lot longer than 2027 for 200B models on local hardware. SOC platforms like Apple Silicon are hamstrung by their obsession over raster performance, the hardware lacks the fundamental GPGPU hardware to be a replacement for real-world inference.
This prediction alone isn’t useful at all without a bound on speed and maybe quantization.
You can already run >200B MoE models on basic consumer hardware by picking a low bpw quantization and then streaming the experts from SSD. There have been a lot of proof of concept demos, but nobody uses them because they’re so slow and the quality is so degraded.
If you’re saying that hardware will catch up by mid-2027, I disagree. The limitation is fast memory and that’s going to be expensive for a while. I have a 128GB unified memory machine that can technically run 200B MoE models with enough quantization, but it’s so slow that there’s no reason to do it. It’s going to be a few years before we have enough RAM and processing power in basic consumer hardware without spending as much as a used car to get it.
> This is a GPT4 level model running locally with a decent speed on a 16gb ram macbook air.
Sorry, but 9 tokens per second with a slow prompt processing speed is not decent for anything other than getting short chat responses.
You’re also not running the full GPT4 quality model. I’m very familiar with that model from some other work and the 4-bit quants are just not as good as all of those KL divergence plots would have you believe.
You also have very short context. It’s basically useless for anything more than short chats where you’re okay watching the output come back at reading speed, skipping the reasoning part (which is important for calling it GPT4 level quality), and waiting a long time for the first token.
Yes, it’s technically running, but not in a way that would be useful by normal LLM standards.
It's quite telling you didn't use Qwen3.6-35B-A3B locally to build that, seems there was another collaborator ;)
Show something you've built with the model+tooling instead, truly dogfood it. I'm sure you'll discover things along the way too!
that would have run into a race condition unfortunately ;)
but there is a sample landing page + a python function on the repo which shows what the model produced. my goal is to integrate the local model in my workflow so that claude/OAI can call this model for basic stuff.
That is no where near decent at all.
If we just take into account output token generation for simplicity. With 5tps u get 180k tokens an hour. That would costs around 0.05USD from an inference provider.
I estimate that the server consumes probably around 500W during inference.
In Germany where 1kwh cost around 0.3USD, 180k tokens inferred locally would therefore cost 0.15USD which is 3x the costs of using an inference provider.
But for ppl who worry about their data, running locally might still be good. However, they should be aware, that it is much less efficient than using an inference provider.
The efficiency gap will also significantly increase as new GPUs will make inference much more efficient.
The privacy nuts have a better leg to stand on, but even then it's hard to believe that they're using on-prem AI to replace SOTA model inference. As cool as local LLMs are, a lot of the stuff people run is a novelty.
https://gist.github.com/hparadiz/f3596d00a62d8ebb2dadcc46ee5...
https://news.ycombinator.com/item?id=48354801
FWIW I'm getting a hardware max of 20 tok/s (approx topping out the GPU's compute) on my custom local diffusiongemma port running on an M3.
A 10 year old Xeon is all you need
https://news.ycombinator.com/item?id=48353348
Whether the writer's setup affects that choice I don't know.
The fix is open upstream as PR #2138 (https://github.com/ikawrakow/ik_llama.cpp/pull/2138), awaiting review. Fair warning on the AI angle: the patch was written by Claude at my direction. The post is explicit about which parts were me and which weren't. Happy to answer questions about either the bug or the workflow.
I don't think the post itself reads like AI at all, but that's just me.
Android studio connected to a local model disconnects automatically after 10 minutes. How set this limit to 12 hours or remove it completely?
I could run my LM studio model all night... but I cant, since Android studio times out after a hard limit of 10M.
This is not related to number of tokens.
I tried Googling, searching for settings in Android studio, even created a stackoverflow post - but zero information. Jetbrains mentions "remote agent timeout mechanism" - but after changing it, nothing happens.
https://docs.ollama.com/faq#how-do-i-keep-a-model-loaded-in-...
You didn't specify what was serving your local model.
Do you know how to switch it in LM studio?
What I see is that: android studio gives "Error: stream failed" and in LM studio server I see it is still working, then says that client (=android studio) disconnected.
So I assumed it was a setting in android studio.