hermes-ai.net

Read docs →
HermesHermes Agent Docs
Back to News

Cerebras Runs Alibaba's Qwen 3.8 27B at 1,850 Tokens per Second

Alibaba's 27B dense multimodal model lands on Cerebras at roughly 1,800 tokens per second, with reasoning on by default and a 128K context on paid tiers.

Cerebras Runs Alibaba's Qwen 3.8 27B at 1,850 Tokens per Second
Source
Cerebras
Published
Author
AlphaSignal Newsroom
Read
1 min read

Alibaba's 27B dense multimodal model lands on Cerebras at roughly 1,800 tokens per second, with reasoning on by default and a 128K context on paid tiers.

Reporting is indexed from AlphaSignal. Rights remain with the original publisher and cited sources.

Read original report