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 |
|---|---|---|
| .. | ||
| src | ||
| w32 | ||
| AUTHORS 2.7 KB | ||
| COPYING 24.1 KB | ||
| MHD_config.h 24.5 KB | ||
| origin.md 1.7 KB | ||