Qwen 3.8 27B available on Cerebras at 1500 tokens/s
inference-docs.cerebras.ai
Qwen 3.8 27B available on Cerebras at 1500 tokens/s
1–10 of 238 posts
Re: Qwen 3.8 27B available on Cerebras at 1500 tokens/s
#2I 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.
Re: Qwen 3.8 27B available on Cerebras at 1500 tokens/s
#3I 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.
Agreed, but in our SAAS I can tell some UX will sky-rocket to next level with this
Re: Qwen 3.8 27B available on Cerebras at 1500 tokens/s
#4Why do they only host small models rather than the 2.4T version? Is the I/O and interconnect between the wafers bad due to the limited beachfront relative to the massive size of the chip?
Re: Qwen 3.8 27B available on Cerebras at 1500 tokens/s
#5Why do they only host small models rather than the 2.4T version? Is the I/O and interconnect between the wafers bad due to the limited beachfront relative to the massive size of the chip?
Mostly economics I'm sure
Re: Qwen 3.8 27B available on Cerebras at 1500 tokens/s
#6used their Code product with GLM4.7. its fun but if the model is bad it just doesn’t do much useful.
Hope they add such models to Code too :)
Re: Qwen 3.8 27B available on Cerebras at 1500 tokens/s
#7Why do they only host small models rather than the 2.4T version? Is the I/O and interconnect between the wafers bad due to the limited beachfront relative to the massive size of the chip?
They make a giant inference chip. Their inference service is basically just advertising for their core value prop: hardware.
The CEO was on Gradient Dissent a couple years ago: https://www.youtube.com/watch?v=qNXebAQ6igs
Re: Qwen 3.8 27B available on Cerebras at 1500 tokens/s
#8I 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
Re: Qwen 3.8 27B available on Cerebras at 1500 tokens/s
#9I 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.
It appears that they do support Prompt Caching: https://inference-docs.cerebras.ai/capabilities/prompt-cachi...
Re: Qwen 3.8 27B available on Cerebras at 1500 tokens/s
#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)).