I'm still sad that we haven't seen a new Taalas style chip a la https://chatjimmy.ai/. Smaller models are good enough now to make that insane burst of tokens so useful.
7-8 figures annual spend will buy a hell of a lot of capable local inference hardware you can own, though it won't be at the absurd token/s rate, you'll be able to run almost anything on it... And it'll still have a good residual resale value after 4 years the way things are going now.
Feel like you could spend 6 figures building out a team and the rest renting compute for a whole year, and get the team to create a local inference solution with that kind of budget…
Lighting my codebase on fire at the speed of light. Like microwaving the spaghetti.
I genuinly only see these speeds being useful for customer service/transactional workflows. Of which much smaller models can do the job (but those dont make tons of money for companies like Cerebras that need to pay off massive amounts of debt).
Nobody needs to code at 600 words per second. Using a 100tps model for an hour or so will leave you with 4-8hrs of code review and revision work.
Human code review? What is this, 2025? The modality today is write with one LLM, review by a different one, (important: two different model families will catch errors one series won't) then deploy right to production.
And if you tell the reviewer the author is a competitors model it becomes extra snarky and vigilant. Then give the review results to the author and tell it it's from the competition and it will also become slightly outraged.
Please do not try to use gpt-oss-120b over Cerebras. It is broken, screws up tool calls most of the time, forgets to end thinking blocks and has all sorts of other issues. The speed is amazing but it is absolutely not worth it, especially at that quite incredible cost. Think: $5–10/minute levels of cost with a single agent, because Cerebras also offers no cache pricing for input tokens at all.
> There is no additional fee for using prompt caching. Input tokens, whether served from the cache or processed fresh, are billed at the standard input token rate for the respective model.
So what he’s saying is correct, there is no separate cache pricing, which by normal standards should be 10% of the cost, which can become exceedingly expensive for anything other than single turn. The way they are stating this is of course strange..
Yea i had some pretty meh results using gpt-oss-120b it in my evals where it should have benefited speed alot but it really under performed what i was expecting.
Pricing at $0.25 and $0.75 already puts its cost well above reasonably reputable inference providers for deepseek v4 flash or qwen 3.8-flash-next or similar class of open weight LLMs that fit in under 170GB of RAM, so I don't see the point. I think this is probably also stupider than laguna s 2.1 which can also be very cheap to serve.
Is it possible to construct a control system where bad, fast and cheap can become good, fast, and cheap through repeated sampling and a strong spec/eval harness?
I am trying to keep an open mind with AI, but I also have little understanding of control theory, trying to learn.
At some point the bottleneck becomes tool calling.. and as such, it's preferably if the model is co-hosted (in the same datacenter, at least) with your code repository and all other reference/context it needs (full documentation for most ecosystems, maybe even a copy of common crawl to minimize web fetch usage, etc)
I have tried using Mercury 2.5 for a lot of my tasks.. but this model just isn't there. It seems to be on par with any 14B model at max. Even GPT-OSS-20B performs way better than this in my own attempts to use it.
I really really wanted to use this because it offers incredible speeds and pricing combinations. But nop.. I still am not using it.. not even for basic tasks.
From what I’ve heard, the issue is more that it’s harder to efficiently share the hardware across diffusion requests, so it’s more expensive to serve.
It sounds like there might be opportunities for local models (not open weight, but actually locally run) to use diffusion for faster responses on weaker hardware that doesn’t need to be shared.
But yea, it’s still a red-ish flag that big labs haven’t invested much in it. I could see Google/Apple getting value of this sort of local model, but maybe there’s enough research behind traditional models that it’s not worth the distraction at this point in time.
You can't think that a small startup versus Anthropic's training setup is anywhere near the same scale to make apples to apples comparisons.
Not sure how the Chinese labs pull it off though using autoregressive models. The secret sauce is probably going to be in the training data.
The main reason Google hasn't switched over to DiffusionGemma is because serving at larger batch sizes loses the speed gains you get from diffusion, and most of the primary use case is serving many users at once off a single device with a large batch size.
If you were to move to on-device low latency... like say in a robot or something, then the story might be different...
Personally, I think it's more that text diffusion is not the ideal driver of an agentic work loop than that text diffusion is a total dead end. I am still hoping to see how it does on authoring and editing with further scaling and optimization. I think the push for AGI has put a bit too much focus on the idea of one general model doing everything.
I used this a few days ago and thought something must be wrong with how fast it was responding. "Mercury 2.5 is below average in intelligence, but well priced when comparing to other models of similar price." this is so funny. So when you have a stupid model that is fast - what do you use it for?
It means something, because it an iterative workflow. If you're willing to burn tokens, it's possible for weaker models to implement tasks by incrementally improving drafts.
I've used it on a few for fun projects and its decent but the speed is crazy to watch.
[0] https://www.cerebras.ai/blog/cerebras-kimi-k2-Enterprise
But it can apparently also run 5.6 Sol
Such a tiny model at that t/s is less impressive than it would have been four months ago.
I genuinly only see these speeds being useful for customer service/transactional workflows. Of which much smaller models can do the job (but those dont make tons of money for companies like Cerebras that need to pay off massive amounts of debt).
Nobody needs to code at 600 words per second. Using a 100tps model for an hour or so will leave you with 4-8hrs of code review and revision work.
So what he’s saying is correct, there is no separate cache pricing, which by normal standards should be 10% of the cost, which can become exceedingly expensive for anything other than single turn. The way they are stating this is of course strange..
https://kamilstanuch.github.io/LLM-token-generation-simulato...
I am trying to keep an open mind with AI, but I also have little understanding of control theory, trying to learn.
I really really wanted to use this because it offers incredible speeds and pricing combinations. But nop.. I still am not using it.. not even for basic tasks.
It's telling that frontier labs like Google toyed around with it but didn't invest further even for their most speed and cost sensitive small models
Still unclear for what, if any use cases this is pareto frontier
It sounds like there might be opportunities for local models (not open weight, but actually locally run) to use diffusion for faster responses on weaker hardware that doesn’t need to be shared.
But yea, it’s still a red-ish flag that big labs haven’t invested much in it. I could see Google/Apple getting value of this sort of local model, but maybe there’s enough research behind traditional models that it’s not worth the distraction at this point in time.
Not sure how the Chinese labs pull it off though using autoregressive models. The secret sauce is probably going to be in the training data.
The main reason Google hasn't switched over to DiffusionGemma is because serving at larger batch sizes loses the speed gains you get from diffusion, and most of the primary use case is serving many users at once off a single device with a large batch size.
If you were to move to on-device low latency... like say in a robot or something, then the story might be different...
K2-Horizon-7B has a diffusion and non-diffusion variant, and they claim the same level of intelligence from both models.
Well priced when compared to other models of similar price, eh?
Are we allowed to call this slop, even if the output is not directly from an LLM?