28th August 2024 - Link Blog
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
- I vibe coded my dream macOS presentation app - 25th February 2026
- Writing about Agentic Engineering Patterns - 23rd February 2026
- Adding TILs, releases, museums, tools and research to my blog - 20th February 2026