I have a prediction. By the mid of 2027, we will have >200B MoE models running on basic consumer hardware.
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.
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).
> on a decent speed
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.
I think that any workflow that requires the user to stare at the tokens being generated live is using it wrong. Delegate, don't stare!
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.
> 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.
This is how I used to think about my 3D printer, but FWIW the way my actual thinking and planning works, print speed really matters. Not for the final print, but for iterative work and test parts, it is obvious that either having a fast printer helps. Having multiple slow printers also helps, but there are only so many areas of a design you can iterate on at once.
At the moment my own LLM use is experimental and iterative, and I definitely favour the faster MoE models for much of what I am doing, even if I might in principle prefer to get the final work done in the slower ones.
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.
I'd rather have slower and better output than worse and faster output.
In 1980s ibm has studied and said why sub-second response needed to maintain the mental flow. That time you send a whole screen unlike unix like character by character. This proves very true even when you deal with form processing. I think that we are dealing with the same issue here.
Keep your mental context in your brain is critical
> 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.
You could suspend it to ram, and only wake it up on request, it takes 2 seconds on my box.
It’s not a cost savings relative to paying API prices even if you’re suspending it.
This is an option if you must run local inference, you’re not sensitive to speed, and the budget is low.
It’s not going to be cheaper than paying API prices for the model though.
We clearly have different goals. I want an LLM to review my code, not the other way around.
I'm sure this exact topic has been argued hundreds of times already on HN, but I think I have a new "possibly agreeable to both sides" perspective on this after having lost man-years to retired corporate code aka "FAIAP, throwaway code"
Let LLMs write the corpo code, as it will be unlikely to still be running in 5-10 years. Frontier AI is already at the point where it writes fewer bugs per LOC than humans. By a lot.
Go ahead and do your bespoke coding on your side-project loves and core libraries... The stuff that will last, anyway.
But if you're working for a corpo and still doing bespoke... That's... not gonna last, I'm afraid. Well, either you remaining there, or that, as it were.
There's a whole spectrum of employment between faceless corporations and personal side projects. AI will replace humans because giant business believe they can do the same work, not because they will actually be able to.
The correctness of an application is limited by your ability to understand and describe what you need. We have a word for an application specification tool so detailed it eliminates all ambiguity. It's called a "programming language".
The mistakes are always in the transfer from human to machine. I still find a high-level programming language to be the best way to express my intent. Humans will make mistakes in the hand-off to AI just like they make mistakes in the hand-off to code, but at least code is deterministic.
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
> another task a lunch break whatever and it will be done when you're back
At 5 tokens per second and unknown prompt processing speed, you may need a very extra long lunch break depending on your codebase.
How do you maintain a flow state during a lunch break? I'm looping with Claude on a scale of minutes. While you're waiting, I'm iterating.
This is like comparing a hammer to a screwdriver and feeling smug because you can hammer nails faster than someone else can drive screws.
These are fundamentally different tools for entirely different applications. They only look similar to people who don't understand the tools or their purpose.
This thread started with me saying "we clearly have different goals" and then being told that I just need to hold the screwdriver differently...
You don't "maintain flow." You eat lunch.
I swear, tech culture has gotten people wanting to work for the machines, rather than the other way round.
Right? Tech should make my work easier. Not have me stressing out even more.
Let the machine do its work while I relax, I’ll check up on it later.
This was a discussion about LLM usage patterns. I'm not opposed to lunch breaks. I'm opposed to being required to take the equivalent of 12 lunch breaks a day while I wait for slow responses.
We aren’t there yet. Not for frontier development work at least.
Except often queued agentic flows must be checked in on. Or to use the comparison, 3D printers are not immune to making spaghetti all night when something goes wrong. (I’m not a 3d printing expert so maybe that is solved now)
It is common for agents to just stop because overload or some API error hijinks.
Or you get a TUI question that is blocking.
In general you’re right though, staring at tokens from agentic is not time well spent.
Some of these I’ve built custom harness around in iterm2 though.
is there a good tool to manage these workloads? batch process a bunch, handle failures, retry things etc?
Filament snaps at 1am and then you have to run print again. 10 hours turn into many days potentially.
I watch tokens to see if it goes in right direction. If model goes off the rails, then it is time to stop and adjust prompt.
[dead]
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.
The slower models seem fine for home lab usecases such as processing document transcriptions and tagging them, for example. I don’t need that to be live, it can just churn overnight.
i am working on making it faster but to me 7-9 tokens/sec feels very good. it was 0 tokens/sec a year ago.
Ignore the haters. What you've done is incredible!
If you’re interested in these projects you should check out the project this was based on: https://github.com/JustVugg/colibri
It says so right in the readme. They’re not hiding anything.
How fast does a human write code?
It's fast if you want to automate things that run independently or overnight. It's slow if you want to iterate code together with it.
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.
>>Yes, it’s technically running, but not in a way that would be useful by normal LLM standards.
What are the LLM standards?
Do you know how many people use perplexity? I know many people who are not software engineers or tech workers and have a LLM subscription for rewriting their stuff (non-native english speakers) in english. There are many use cases for running good models locally. Maybe not for you, but someone might find this beneficial.
I have a free perplexity account from some promotion. Not sure what comparison you’re trying to make because Perplexity’s whole thing is that it’s really fast. It launches the search with parallel agents and then even seems to render some of the output paragraphs with parallel sessions to get the results.
Doing the same thing at 7-9 tokens per second, concurrency of 1, would take ages for all of the tool calling and subsequent processing.
It wouldn’t compare in any meaningful way, because perplexity delivers instant results. That’s what I meant by modern standards of LLM usefulness.
That is awesome!
I am curious about the decision to not use GPU since this is for Apple Silicon.
Wouldn't the GPU potentially accelerate the DeltaNet/attention layers and matrix multiplication in general?
It will, but the process at this point is SSD bound rather than compute bound. On a bigger machine, Apple silicon must help but I don't have a bigger machine. I can think about this more and will make changes if that helps.
Downloading now just 'cause the repo name
How are the thermals? I noticed that running any serious workload locally heats system fast.
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).
> I am running Qwen3.6-35B-A3B locally on my 16GB mac with 7-9 tokens/second. Link - https://github.com/deepanwadhwa/samosa-chat
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!
Nothing says they're using Qwen for local development. They could be using it to for conversations, knowledge, or "creative writing."
> Nothing says they're using Qwen for local development
I know! That's my point! You're a poor salesman of a coding environment/tool if you don't even use it yourself for coding...
>>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.
> that would have run into a race condition unfortunately ;)
Not really, you start small, bootstrap as soon as you can, and off you go. Requires a good model though ;)
By early 2028, major players like Intel, AMD, QC will ship accelerators in consumer laptops capable of running ~1T MoE models at ~100 tok/s
Literally the only way this is going to happen is if aliens come to earth and gift us some amazing technology.
Unless there are major improvements to how much hardware it takes to run a 1T model, this is deeply unrealistic. First because why release hardware that puts your biggest customers (data centers) out of business. Second because as I understand it the data centers have bought up all the high end chip production capacity for at least the next year and unless the bubble pops that'll continue for a while.
Because for the company that will actually do it, their biggest customers aren’t data centers they are iPhone owners.
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.
You are comparing a 35B models to a 635B+ frontier model, of course thats not even close
I'm not lamenting that they aren't close, I'm saying Qwen will frequently output code that isn't even syntactically correct, even when the syntax is simple. Which makes it unusable for coding.
To be fair, they don't have the text editor highlighting all the matching parens. I'd be lost too.
Yeah prediction models and many parentheses are probably not a good combination, but we're not talking about anything exceptionally complicated here. I have had syntax issues in Python as well.
It really depends on the language, popular languages work pretty good
try q8, check your parameters. qwen3.6-35b-a3b should definitely be able to do so with no issues at all.
> I am running Qwen3.6-35B-A3B locally on my 16GB mac with 7-9 tokens/second.
That is no where near decent at all.
it's a 16GB machine. i am proud of this machine so far.