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: our promise (built for ourselves first, a small team in England, supported for as long as people use it, a full roadmap soon)
1picassoai513ea9372015
diff --git a/README.md b/README.mdindex f530a41..9466079 100644--- a/README.md+++ b/README.md@@ -74,6 +74,12 @@ Your Mac and your prompt move the numbers; the [release notes](docs/releases/0.5---+## Our promise++**We built Coachwhip for ourselves first: a fast, private way to run a big coding model on a Mac. It worked well enough that we wanted everyone to have it, so we made it open source.**++**We're a small team in England, UK, and we'll keep supporting Coachwhip for as long as people use it. Every issue gets read and answered, and every real bug gets fixed. A full roadmap of the features we're working on is coming soon.**+## Why we built itTwo reasons, and both had to hold at once.@@ -132,6 +138,8 @@ Release notes, every version: [docs/releases](docs/releases).## Roadmap+What's next, while the full roadmap is being written:+- More MoE families: Mixtral, Qwen2-MoE, OLMoE, DeepSeek, GLM, Qwen3.8.- Fused-attention GGUF files.- An adapter that reads your own repository, on your own machine.