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 |
|---|---|---|
| .. | ||
| data.c 5.8 KB | ||
| fetch.c 5.2 KB | ||
| github.h 5.5 KB | ||
| layouts.c 6.9 KB | ||
| main.c 3.0 KB | ||
| read.c 12.1 KB | ||
| README.md 4.0 KB | ||
| repo.c 2.6 KB | ||
| seen.c 2.6 KB | ||
| tools.c 11.5 KB | ||