bitsandbytes Files

Accessible large language models via k-bit quantization for PyTorch

This is an exact mirror of the bitsandbytes project, hosted at https://github.com/bitsandbytes-foundation/bitsandbytes. SourceForge is not affiliated with bitsandbytes.

The interactive file manager requires Javascript. Please enable it or use sftp or scp.
You may still browse the files here.

Name	Modified	Size	InfoDownloads / Week
Parent folder
0.48.2 source code.tar.gz	2025-10-29	304.1 kB	0
0.48.2 source code.zip	2025-10-29	392.5 kB	0
README.md	2025-10-29	552 Bytes	0
Totals: 3 Items		697.1 kB	0

What's Changed

Fix indexing overflow issue for blockwise quantization by @matthewdouglas in https://github.com/bitsandbytes-foundation/bitsandbytes/pull/1784
Fix regression with CPU/disk offloading for accelerate + int8 by @matthewdouglas in https://github.com/bitsandbytes-foundation/bitsandbytes/pull/1786
XPU: Add Windows build for SYCL kernels by @matthewdouglas in https://github.com/bitsandbytes-foundation/bitsandbytes/pull/1787

Full Changelog: https://github.com/bitsandbytes-foundation/bitsandbytes/compare/0.48.1...0.48.2

Source: README.md, updated 2025-10-29

Other Useful Business Software

Powerful App Monitoring Without Surprise Bills

AppSignal starts at $23/month with all features included. No overages, no hidden fees. 30-day free trial.

Tired of monitoring tools that punish you for scaling? AppSignal offers transparent, predictable pricing with every feature unlocked on every plan. Track errors, monitor performance, detect anomalies, and manage logs across Ruby, Python, Node.js, and more. Trusted by developers since 2012 with free dev-to-dev support. No credit card required to start your 30-day trial.

Try AppSignal Free

Gemini 3 and 200+ AI Models on One Platform

Access Google's best plus Claude, Llama, and Gemma. Fine-tune and deploy from one console.

Build generative AI apps with Vertex AI. Switch between models without switching platforms.

Start Free

Featured

Gemini 3 and 200+ AI Models on One Platform

Access Google's best plus Claude, Llama, and Gemma. Fine-tune and deploy from one console.

Build generative AI apps with Vertex AI. Switch between models without switching platforms.

Start Free

Recommended Projects

ChatGLM-6B
ChatGLM-6B: An Open Bilingual Dialogue Language Model
BitNet
BitNet: Scaling 1-bit Transformers for Large Language Models
AutoGPTQ
An easy-to-use LLMs quantization package with user-friendly apis
Mixtral offloading
Run Mixtral-8x7B models in Colab or consumer desktops
Xtuner
A Next-Generation Training Engine Built for Ultra-Large MoE Models

bitsandbytes Files

Accessible large language models via k-bit quantization for PyTorch

Get an email when there's a new version of bitsandbytes

What's Changed