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.

8 labels
bug
Something isn't working
0 open issues
documentation
Improvements or additions to documentation
0 open issues
duplicate
This already exists
0 open issues
enhancement
New feature or request
0 open issues
good first issue
Good for newcomers
0 open issues
help wanted
Extra attention is needed
0 open issues
question
Further information is requested
0 open issues
wontfix
This will not be worked on
0 open issues