bitsandbytes-foundation / bitsandbytes
Accessible large language models via k-bit quantization for PyTorch.
Why this job: matched by what the repo talks about: model, quantization, large, bit
What it does
The library includes quantization primitives for 8-bit & 4-bit operations, through bitsandbytes.nn.Linear8bitLt and bitsandbytes.nn.Linear4bit and 8-bit optimizers through bitsandbytes.optim module.
Get started
No single install command. Read the steps in the README (opens in new tab)
- Maintenance
- Active
- Last commit 16 days ago
- Stars
- 8,537
- +4 this week
- Licence
- MIT
- Allows business use
- Downloads for
- None listed
- No release files
- Latest version
- 0.50.2
- Released 2 months ago
- Built with
- Python
- 68% of the code
Is it looked after?
- Contributors
- Not stated
- Last 90 days
- Issues
- 96% closed
- 55 still open
- Pull requests
- 509 merged
- 66 waiting
- Releases
- 36
- 7 in the last year
Similar repos
| Repo | Stars | Last commit | Licence | Downloads for |
|---|---|---|---|---|
| lyogavin / airllm | 42,201 | yesterday | Apache-2.0 | No downloads |
| Epistates / pmetal | 332 | 10 days ago | Custom | Mac |
| jy-yuan / KIVI | 439 | 11 months ago | MIT | No downloads |
More: languages, topics, project record and preview image
Languages
- Python 68%
- Cuda 20%
- C++ 10%
- CMake 2%
Topics
- llm
- machine-learning
- pytorch
- qlora
- quantization
Project record
- JobLocal LLMs
- StatusListed
- Commits1,221
- Forks946
- Watching51
- Stars in 28 days+24
- CreatedJun 4, 2021
- First seen by usNov 7, 2026
- CheckedNov 8, 2026