Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Cerebras Code now supports GLM 4.6 at 1000 tokens/sec

cerebras.ai

Post reply on HN
Print view View original

31–40 of 135 posts

Re: Cerebras Code now supports GLM 4.6 at 1000 tokens/sec

#31

Post by gardnr »

odie5533 wrote: post #29

I find the fast models good for rapidly iterating UI changes with voice chat. Like "add some padding above the text box" or "right align the button". But I find the fast models useless for deep coding work. But a fast model has its place. Not $50/month though. Cursor has Compose 1 and Grok Code Fast for free. Not sure what $50/month gets me that those don't. I liked the stealth supernova model a lot too.

GLM 4.6 isn't a "fast" model. It does well in benchmarks vs Sonnet 4.5.

Cerebras makes a giant chip that runs inference at unreal speeds. I suspect they run their cloud service more as an advertising mechanism for their core business: hardware. You can hear the founder describing their journey:

https://podcasts.apple.com/us/podcast/launching-the-fastest-...

Re: Cerebras Code now supports GLM 4.6 at 1000 tokens/sec

#32

Post by behnamoh »

typpilol wrote: post #27
bigyabai wrote: post #7

Earlier quoted context omitted.

For $50/month, it's a non-starter. I hope they can find a way to use all this excess bandwidth to put out a $10 equivalent to Claude Code instead of a 1000 tok/s party trick I can't use properly.

I feel the same and it's also why I can't understand all these people using small local models. Every local model I've used and even most open source are just not good

the only good-enough model I still use it gpt-oss-120b-mxfp4 (not 20b) and glm-4.6 at q8 (not q4).

quantization ruins models and some models aren't that smart to begin with.

Re: Cerebras Code now supports GLM 4.6 at 1000 tokens/sec

#33

Post by namanyayg »

mythz wrote: post #28

AI moves so fast that Vibe Coding still has a negative stigma attached to it, but even after 25 years of development, I'm not able to match the productivity of getting AI to implement the features I want. It's basically getting multiple devs to set out and go do work for you where you just tell them what you want and provide iterative feedback till they implement all the features you want, in the way you want and to…

Exactly, Codex gpt-5-high is quite like sending smart devs. It still makes mistakes, and when it does they're extremely stupid ones, but I am now accepting the code it generates as throwable and I just reroll when it does something dumb.

Re: Cerebras Code now supports GLM 4.6 at 1000 tokens/sec

#34

Post by NitpickLawyer »

behnamoh wrote: post #4

If they don't quantize the model, how do they achieve these speeds? Groq also says they don't quantize models (and I want to believe them) but we literally have no way to prove they're right. This is important because their premium $50 (as opposed to $20 on Claude Pro or ChatGPT Plus) should be justified by the speed. GLM 4.6 is fine but I don't think it's still at the GPT-5/Claude Sonnet 4.5 level, so if I'm paying…

> What kind of workflow justifies this? I'm genuinely curious.

Any workflow where verification is faster / cheaper than generation. If you have a well tested piece of code and want to "refactor it to use such and such paradigme", you can run n faster model queries and pick the fastest.

My colleagues that do frontend use faster models (not this one specifically, but they did try fast-code-1) to build components. Someone worked out a workflow w/ worktrees where the model generates n variants of a component, and displays them next to each other. A human can "at a glance" choose which one they like. And sometimes pick and choose from multiple variants (something like passing it to claude and say "keep the styling of component A but the data management of component B"), and at the end of the day is faster / cheaper than having cc do all that work.

Re: Cerebras Code now supports GLM 4.6 at 1000 tokens/sec

#35

Post by NitpickLawyer »

behnamoh wrote: post #23
nine_k wrote: post #18

Earlier quoted context omitted.

> What kind of workflow justifies this? Think about waiting for compilation to complete: the difference between 5 minutes and 15 seconds is dramatic. Same applies to AI-based code-wrangling tasks. The preserved concentration may be well worth the $50, especially when paid by your employer.

they should offer a free trial so we build confidence in the model quality (e.g., to make sure it's not nerfed/quantized/limited-context/etc.).

You can usually use them with things like openrouter. Load some credits there and use the API in your preferred IDE like you'd use any provider. For some quick tests it's probably be <5$ for a few coding sessions so you can check out the capabilities and see if it's worth it for you.

Re: Cerebras Code now supports GLM 4.6 at 1000 tokens/sec

#36

Post by NitpickLawyer »

prodigycorp wrote: post #11
niklassheth wrote: post #8

This is more evidence that Cognition's SWE-1.5 is a GLM-4.6 finetune

Can you provide more context for this? (eg Was SWE-1.5 released recently? Is it considered good? Is it considered fast? Was there speculation about what the underlying model was? How does this prove that it's a GLM finetune?)

People saw chinese characters in generations made by swe-1.5 (windsurfs model) and also in the one made by cursor. This led to suspicions that the models are finetunes of chinese models (which makes sense, as there aren't many us/eu strong coding models out there). GLM4.5/4.6 are the "strongest" coding models atm (with dsv3.2 and qwen somewhat behind) so that's where the speculation came from. Cerebras serving them at roughly the same speeds kinda adds to that story (e.g. if it'd be something heavier like dsv3 or kimik2 it would be slower).

Re: Cerebras Code now supports GLM 4.6 at 1000 tokens/sec

#37

Post by dust42 »

mythz wrote: post #28

AI moves so fast that Vibe Coding still has a negative stigma attached to it, but even after 25 years of development, I'm not able to match the productivity of getting AI to implement the features I want. It's basically getting multiple devs to set out and go do work for you where you just tell them what you want and provide iterative feedback till they implement all the features you want, in the way you want and to…

It just depends on what you are doing. A green field react app in typescript with a CRUD API behind? The LLMs are a mind blowing assistant and 1000t/s is crazy.

You are doing embedded development or anything else not as mainstream as web dev? LLMs are still useful but no longer mind blowing and often produce hallucinations. You need to read every line of their output. 1000t/s is crazy but no longer always in a good way.

You are doing stuff which the LLMs haven't seen yet? You are on your own. There is quite a bit of irony in the fact that the devs of llama.cpp barely use AI - just have a look at the development of support for Qwen3-Next-80B [1].

[1] https://github.com/ggml-org/llama.cpp/pull/16095

Re: Cerebras Code now supports GLM 4.6 at 1000 tokens/sec

#38

Post by arresin »

odie5533 wrote: post #29

I find the fast models good for rapidly iterating UI changes with voice chat. Like "add some padding above the text box" or "right align the button". But I find the fast models useless for deep coding work. But a fast model has its place. Not $50/month though. Cursor has Compose 1 and Grok Code Fast for free. Not sure what $50/month gets me that those don't. I liked the stealth supernova model a lot too.

Composer and grok fast are not free.

Re: Cerebras Code now supports GLM 4.6 at 1000 tokens/sec

#39

Post by behnamoh »

NitpickLawyer wrote: post #35
behnamoh wrote: post #23

Earlier quoted context omitted.

they should offer a free trial so we build confidence in the model quality (e.g., to make sure it's not nerfed/quantized/limited-context/etc.).

You can usually use them with things like openrouter. Load some credits there and use the API in your preferred IDE like you'd use any provider. For some quick tests it's probably be <5$ for a few coding sessions so you can check out the capabilities and see if it's worth it for you.

openrouter charges me $12 on a $100 credit...

Re: Cerebras Code now supports GLM 4.6 at 1000 tokens/sec

#40

Post by almostgotcaught »

dust42 wrote: post #37
mythz wrote: post #28

AI moves so fast that Vibe Coding still has a negative stigma attached to it, but even after 25 years of development, I'm not able to match the productivity of getting AI to implement the features I want. It's basically getting multiple devs to set out and go do work for you where you just tell them what you want and provide iterative feedback till they implement all the features you want, in the way you want and to…

It just depends on what you are doing. A green field react app in typescript with a CRUD API behind? The LLMs are a mind blowing assistant and 1000t/s is crazy. You are doing embedded development or anything else not as mainstream as web dev? LLMs are still useful but no longer mind blowing and often produce hallucinations. You need to read every line of their output. 1000t/s is crazy but no longer always in a good w…

I've said it before but no one takes it seriously: LLMs are only useful if you're building something that's already in the training set ie already commodity. In which case why are you building it???
Post reply on HN