Sign in Sign up
pypi

fermion-research

Sub-2-bit models from Fermion Research: chat with a ~2 GB 8B language model at native-runtime speed, transcribe speech on Apple silicon or a plain CPU, and serve either on an OpenAI-compatible endpoint

pypi View on Pypi

Activity

Latest release
1w ago
Total releases
20
Cadence
~daily
Last 12 months
20

Details

License
Apache-2.0
First release
Jul 27, 2026
Releases
Version Released
0.1.24 patch
0.1.23 patch
0.1.22 patch
0.1.21 patch
0.1.20 patch
0.1.19 patch
0.1.18 patch
0.1.17 patch
0.1.16 patch
0.1.15 patch
0.1.14 patch
0.1.13 patch
0.1.12 patch
0.1.11 patch
0.1.10 patch
0.1.9 patch
0.1.8 patch
0.1.7 patch
0.1.6 patch
0.1.5 initial