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.
Stars
437
Today
+6
last 24 hours
This week
+6
Forks
34
Clone
git clone https://github.com/prabanta-dev/janas.gitStar growth
- Created
- 2026-09-20
- Last commit
- 2026-10-14
- Gained since tracking
- +6
Updated Sun, 18 Oct 2026 15:32:30 GMT · description from the project itself