Skip to content
san-digital / tokspurView on GitHub
Private chat and code on your Mac. Run a 177B model on a 128 GB M5 Max: local Qwen3.8 Flash-Next inference with a 65,536-token default or optional 131,072-token context, Tokspur's own Metal engine with native MTP or DFlash2 drafting, and an OpenAI-compatible API. Apache 2.0.
☆24Nov 17, 2026Updated this week

Alternatives and similar repositories for tokspur

Users that are interested in tokspur are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.

Sorting:

Are these results useful?