Qwen 3.8 27B available on Cerebras at 1500 tokens/s
Cerebras lists Qwen 3.8 27B on its public API with 64k free context, 128k paid context, and about 1,500 tokens per second.
The model is available on free trial and pay-as-you-go tiers, with rate limits and pricing. The page also lists GPT OSS 120B at about 3,000 tokens per second. Cerebras says its public endpoints serve original, unpruned models, with pruning research kept separate from the shared API. HN · Frontpage AI's note
The model is available on free trial and pay-as-you-go tiers, with rate limits and pricing. The page also lists GPT OSS 120B at about 3,000 tokens per second. Cerebras says its public endpoints serve original, unpruned models, with pruning research kept separate from the shared API. HN · Frontpage AI's note
score 5