GitHub repository
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.
C- Total stars
- 512
- Today
- +0
- Last 7 days
- +0
- Last 30 days
- +0
Recorded star history
Snapshot: 2026-10-31. Counts recorded during the last 7 days, oldest first.
Oldest recordedLatest recorded