IST-DASLab / GSQ
Gumbel-Softmax post-training quantization for LLMs (1–3 bit scalar, INT/GGUF-compatible).
Why this job: says: gguf; topics: gguf, quantization
What it does
GSQ pushes the size-vs-accuracy Pareto frontier across model scales and bit widths, matching or beating prior scalar PTQ methods at the same footprint and closing most of the gap to vector-quantized baselines.
Get started
curl -LsSf https://astral.sh/uv/install.sh | sh - Maintenance
- Active
- Last commit 4 months ago
- Stars
- 132
- +5 this week
- Licence
- Apache-2.0
- Allows business use
- Downloads for
- None listed
- No release files
- Latest version
- None yet
- No releases
- Built with
- Python
- 93% of the code
Is it looked after?
- Contributors
- 0
- Last 90 days
- Issues
- 22% closed
- 7 still open
- Pull requests
- 2 merged
- 1 waiting
- Releases
- None
- Never published
- No contributing guide
- No security policy
- No code of conduct
Similar repos
| Repo | Stars | Last commit | Licence | Downloads for |
|---|---|---|---|---|
| timtoole02 / Camelid | 220 | 24 days ago | MIT | Mac, Windows, Linux |
| mw00 / project-maya | 2,712 | 2 days ago | MIT | No downloads |
| antirez / gguf-tools | 373 | 5 months ago | MIT | No downloads |
More: languages, topics and project record
Languages
- Python 93%
- Shell 7%
Topics
- gguf
- llm
- post-training-quantization
- quantization
Project record
- JobLocal LLMs
- StatusListed
- Commits51
- Forks22
- Watching1
- Stars in 28 days+40
- CreatedMay 12, 2026
- First seen by usNov 7, 2026
- CheckedNov 9, 2026