Re:Qwen 3.8 27B available on Cerebras at 1500 tokens/s
by codazoda on Thursday September 03, 2026 @05:21PM
(#49557228)
Got it. But, they also charge the same for cached tokens, so that probably closes the gap on Foundation models quite a bit.
[ Parent
| on HN ]
Re:Qwen 3.8 27B available on Cerebras at 1500 tokens/s
by ma2kx on Thursday September 03, 2026 @09:45PM
(#49559521)
I guess Cerebras didnt intend the model for agentic coding but rather for small one shot task like title generation. At least thats why I use the free tier for.
Re:Qwen 3.8 27B available on Cerebras at 1500 tokens/s
by low_tech_punk on Friday September 04, 2026 @07:10AM
(#49563019)
my hunch is that their hardware can't cache