Cerebras Inference: AI at Instant Speed (via) New hosted API for Llama running at absurdly high speeds: "1,800 tokens per second for Llama3.1 8B and 450 tokens per second for Llama3.1 70B".
How are they running so fast? Custom hardware. Their WSE-3 is 57x physically larger than an NVIDIA H100, and has 4 trillion transistors, 900,000 cores and 44GB of memory all on one enormous chip.
Their live chat demo just returned me a response at 1,833 tokens/second. Their API currently has a waitlist.
Recent articles
- Video + notes on upgrading a Datasette plugin for the latest 1.0 alpha, with help from uv and OpenAI Codex CLI - 6th November 2025
- Code research projects with async coding agents like Claude Code and Codex - 6th November 2025
- A new SQL-powered permissions system in Datasette 1.0a20 - 4th November 2025