LINKED LIST [txt mode] ▸ Llama 3.1 405B now runs at 969 tokens...
home explore | log in

Llama 3.1 405B now runs at 969 tokens/s on Cerebras Inference

news.ycombinator.com · 2026-10-06 · 0 upvotes

log in to save, upvote or flag this.


─── In 0 lists ─────────────────────────────────────────

(not in any lists yet)

* Llama 3.1 405B now runs at 969 tokens/s on Cerebras Inference (discussion)