37 tok/s from Qwen3-Next-80B (48 GB) on a 32 GB laptop, 24 without drafts vs 2.8 for llama.cpp; reading 62 vs 16 tok/s. Faster than llama.cpp on all 13 models compared in Q4_K_M. LLMs bigger than your RAM, pure C, CPU or GPU.
C avx2ccpu-inferenceggufinference-enginelinuxllmlocal-llmmixture-of-expertsmoenvmequantizationqwen3simdspeculative-decodingvulkan
| Name | Last commit message | Last commit date |
|---|---|---|
| .github | ||
| dist | ||
| docs | ||
| examples | ||
| include | ||
| src | ||
| tests | ||
| tools | ||
| .clang-format 602 B | ||
| .gitignore 340 B | ||
| AUTHORS 2.0 KB | ||
| build.sh 28.8 KB | ||
| ChangeLog.md 320 KB | ||
| CONTRIBUTING.md 3.3 KB | ||
| INSTALL.md 9.7 KB | ||
| LICENSE 34.3 KB | ||
| MODELS.md 22.5 KB | ||
| README.md 34.1 KB |