Lithos 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.
We’re open-sourcing lithos-metal 🚀
Megakernels + DSpark speculative decoding run Qwen3.8-27B at 200+ tokens/s/user peak on one @Apple M5 Max.
Ultra-fast inference on your laptop. Try it with any coding agent in one command.
Code: https://github.com/lithos-ai/lithos-metal
Tech blog: https://www.lithosai.com/blog/lithos-metal
Source: Zhihao Jia · x.comPublished · added here
