The 80B Qwen3-Coder-Next on a 16 GB Mac, about 13 tok/s, fully offline. A mixture-of-experts inference engine for Apple silicon.
Rust
README: badges that apply (release, license, macOS on Apple silicon)
1picassoai4a442b5efe23
diff --git a/README.md b/README.mdindex d9b6dfc..1ef1116 100644--- a/README.md+++ b/README.md@@ -1,5 +1,10 @@<p align="center"><img src="docs/coachwhip.png" alt="A coachwhip snake on sand" width="720"></p>+<p align="center">+ <a href="https://github.com/1picassoai/coachwhip/releases/latest"><img src="https://img.shields.io/github/v/release/1picassoai/coachwhip" alt="Latest release"></a>+ <a href="LICENSE"><img src="https://img.shields.io/github/license/1picassoai/coachwhip" alt="License: Apache-2.0"></a>+ <img src="https://img.shields.io/badge/macOS-Apple%20silicon-black?logo=apple" alt="macOS on Apple silicon"></p>+# Coachwhip**Run mixture-of-experts models that are bigger than your memory.**