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
Activity
- Latest release
- 1w ago
- Total releases
- 20
- Cadence
- ~daily
- Last 12 months
- 20
Details
- License
- Apache-2.0
- First release
- Jul 27, 2026
| Version | Released | |
|---|---|---|
0.1.24
patch
|
0.1.24
patch
Dependencies (4)
|
|
0.1.23
patch
|
0.1.23
patch
Dependencies (4)
|
|
0.1.22
patch
|
0.1.22
patch
Dependencies (4)
|
|
0.1.21
patch
|
0.1.21
patch
Dependencies (4)
|
|
0.1.20
patch
|
0.1.20
patch
Dependencies (4)
|
|
0.1.19
patch
|
0.1.19
patch
Dependencies (4)
|
|
0.1.18
patch
|
0.1.18
patch
Dependencies (4)
|
|
0.1.17
patch
|
0.1.17
patch
Dependencies (4)
|
|
0.1.16
patch
|
0.1.16
patch
Dependencies (4)
|
|
0.1.15
patch
|
0.1.15
patch
Dependencies (4)
|
|
0.1.14
patch
|
0.1.14
patch
Dependencies (4)
|
|
0.1.13
patch
|
0.1.13
patch
Dependencies (4)
|
|
0.1.12
patch
|
0.1.12
patch
Dependencies (4)
|
|
0.1.11
patch
|
0.1.11
patch
Dependencies (4)
|
|
0.1.10
patch
|
0.1.10
patch
Dependencies (4)
|
|
0.1.9
patch
|
0.1.9
patch
Dependencies (4)
|
|
0.1.8
patch
|
0.1.8
patch
Dependencies (4)
|
|
0.1.7
patch
|
0.1.7
patch
Dependencies (4)
|
|
0.1.6
patch
|
0.1.6
patch
Dependencies (4)
|
|
0.1.5
initial
|
0.1.5
initial
Dependencies (4)
|