lithos-metal

AILithos AI says it is open-sourcing lithos-metal, which uses megakernels and DSpark speculative decoding. The post claims Qwen3.8-27B reaches a peak of over 200 tokens per second per user on a single Apple M5 Max. It says users can try the tool with any coding agent in one command, and links to the code on GitHub and a technical blog.

Why it matters: Megakernels and DSpark speculative decoding, reported at 200+ tokens/s per user peak for Qwen3.8-27B on one Apple M5 Max

Descriptions are prepared from the linked sources. Inclusion is not an endorsement.