GitHub · C
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.
- Stars
- 735
- Forks
- 73
- Stars gained in 24 hours
- 0
- Forks gained in 24 hours
- 0
Topics: avx2, c, cpu-inference, gguf, inference-engine, linux, llm, local-llm, mixture-of-experts, moe
Latest data point: Nov 21, 2026 · 735 stars · 73 forks