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
| Name | Last commit message | Last commit date |
|---|---|---|
| .. | ||
| 0.3.0.md 2.5 KB | ||
| 0.4.0.md 4.2 KB | ||
| 0.4.1.md 1.0 KB | ||
| 0.5.0.md 3.3 KB | ||
| 0.5.1.md 3.7 KB | ||
| 0.5.2.md 2.3 KB | ||
| 0.5.3.md 2.4 KB | ||