Qwen 3.8 27B available on Cerebras at 1500 tokens/s • Hacker News Board

Re: Qwen 3.8 27B available on Cerebras at 1500 tokens/s

#21

Post by bakies » Thu, Sep 03, 2026, 6:58 PM UTC

peri-cl wrote: post #10

(Was anyone able to create an account just now? I tried but onboarding falls into a redirect loop) (update: I got my answer. support@ replied and said my email domain is on their blacklist. It was just me (and I've resolved it)).

yeah - used sign in with google

Re: Qwen 3.8 27B available on Cerebras at 1500 tokens/s

#22

Post by polygot » Thu, Sep 03, 2026, 6:59 PM UTC

Ut oh, might be down: "Unable to connect to the server. Please check your connection and try again." when sending a message to Qwen 3.8 27B.

Re: Qwen 3.8 27B available on Cerebras at 1500 tokens/s

#23

Post by vb-8448 » Thu, Sep 03, 2026, 7:00 PM UTC

At that speed it's too pricey for agentinc tasks.

Re: Qwen 3.8 27B available on Cerebras at 1500 tokens/s

#24

Post by londons_explore » Thu, Sep 03, 2026, 7:02 PM UTC

foundfontic wrote: post #8

I really wish they had their customer support somewhere else than Discord, which seems to think I'm a bot and doesen't accept my email or phone numbe

discord support can fix such issues

Re: Qwen 3.8 27B available on Cerebras at 1500 tokens/s

#25

Post by dshat » Thu, Sep 03, 2026, 7:02 PM UTC

I'm saddened that Gemma4 is replaced by Qwen 3.8 on PayGo plan. Gemma4 31B is not coding model but it is excellent at intent understanding and task execution used in agentic software. This just shows that real world dominant usage for llms so far is to code generate. And not to augment business products. They must had barely anyone using Gemma to remove it from that tier.

Re: Qwen 3.8 27B available on Cerebras at 1500 tokens/s

#26

Post by verdverm » Thu, Sep 03, 2026, 7:03 PM UTC

scotty79 wrote: post #15

trvz wrote: post #13

Normal people: tok/s or t/s Psychopaths: tok/SEC

I like tps

do you get reports on them?

Re: Qwen 3.8 27B available on Cerebras at 1500 tokens/s

#27

Post by eli » Thu, Sep 03, 2026, 7:04 PM UTC

gardnr wrote: post #2

I used their Coding Plan for a few months. It is genuinely difficult to keep up with the models. The output is so fast. Qwen 3.8 27B is likely one of the strongest models they've hosted so far. Edit: it looks like this is only available on a API token pricing. Does anyone know if they have rolled out prompt caching yet? It used to get pretty expensive for agentic coding tasks with no prompt caching.

Strongest model that they host on the public endpoint. They do a super fast version of GPT 5.6 Sol for OpenAI and have bigger open models on dedicated endpoints.

Re: Qwen 3.8 27B available on Cerebras at 1500 tokens/s

#28

Post by singpolyma3 » Thu, Sep 03, 2026, 7:04 PM UTC

gardnr wrote: post #2

I used their Coding Plan for a few months. It is genuinely difficult to keep up with the models. The output is so fast. Qwen 3.8 27B is likely one of the strongest models they've hosted so far. Edit: it looks like this is only available on a API token pricing. Does anyone know if they have rolled out prompt caching yet? It used to get pretty expensive for agentic coding tasks with no prompt caching.

The coding plan is gone now right?

Re: Qwen 3.8 27B available on Cerebras at 1500 tokens/s

#29

Post by eli » Thu, Sep 03, 2026, 7:04 PM UTC

byako wrote: post #18

[flagged]

If you read the reasoning trace for Qwen 3.8, it does a whole lot of "uh" and "But, wait..." too

Re: Qwen 3.8 27B available on Cerebras at 1500 tokens/s

#30

Post by miohtama » Thu, Sep 03, 2026, 7:05 PM UTC

byako wrote: post #18

[flagged]

Your brain can wash laundry and cook pasta, so there is still a long way to go