Skip to content

armgit / janas

Public Imported from GitHub
0

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.

Commits on main

6476bbc
97149f4
02c325e
4534903
Release 2026-09-27: janas-try tries Gemma
camauri committed 1 month ago
5d8e288
61de67d
Release 2026-09-26: why no GPU is used
camauri committed 1 month ago
791b07d
Janas-LLM: first public release
camauri committed 2 months ago
87933b3