AlphaUncommon
prabanta-dev/janas
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.
- Owner
- prabanta-dev (organization)
- Stars
- Stars: 570
- Forks
- Forks: 49
- Language
- C
- License
- GPL-3.0
- Created
- 2026
- Topics
- avx2ccpu-inferenceggufinference-enginelinuxllmlocal-llmmixture-of-expertsmoe
- Tier
- Alpha (250 to 699 ★) What this tier means
Nearby in C
All C repos- postgrespro/zsonStars: 570CAlpha
- oscarpilote/Ortho4XPStars: 570CAlpha
- xdp-project/bpf-examplesStars: 570CAlpha