Hacker News·2 min read·hard
Qwen 3.8 27B available on Cerebras at 1500 tok/SEC
A
altertable
✦AI Summary
Cerebras has added the Qwen 3.8 27B model to its public API endpoints, offering high-speed inference capabilities. The platform maintains a policy of serving unpruned, original versions of open-source models to its users.
Why it matters
High-performance inference platforms are essential for developers looking to deploy large language models efficiently at scale.
On this page Available Models Model Compression Frequently Asked Questions Copy page Copy MCP Server View as Markdown Models Model Catalog Model Catalog Browse all models available on Cerebras public endpoints.
technologybusiness
✦
Get smarter about the news
Sign up free for a feed built around what you actually care about, Dive Deeper research on any story, and the full text of every article.
Create free accountAlready have an account? Sign in