The easiest way to run an open model on your own machine: one command downloads and starts it, plus a local REST API and libraries for Python and JavaScript.
All repositories
Open models & inferencebitsandbytes-foundation
bitsandbytes
Squeezes models down to 8 and 4 bits so they fit on an ordinary GPU. QLoRA and running large models in half the memory both rely on it.
Who it is for
For people fine-tuning or running large models on limited memory.
How to start
- Check the requirements: Python 3.10+ and PyTorch 2.4+.
- Use 4-bit layers via
bitsandbytes.nn.Linear4bitor 8-bit ones viaLinear8bitLt. - Cut training memory with the 8-bit optimizers from
bitsandbytes.optim.
Steps are taken from the README. Check the current version in the repository before running them.
Stars over the last 30 days
+57Sep 6 — Oct 6
Author's description
Accessible large language models via k-bit quantization for PyTorch.
More in «Open models & inference»
The core library for working with models: one codebase for text, vision, audio and multimodal tasks, for both inference and training. Most new open models ship through it.
A self-hosted ChatGPT-style interface that connects to Ollama and any OpenAI-compatible API. Installs with a single Docker command and runs on your own server.
A C/C++ engine that runs language models on ordinary hardware: laptops, phones, GPU-less servers. Much of local AI, Ollama included, is built on it.
Repository of the large open DeepSeek-V3 mixture-of-experts model: description, benchmark results and run instructions. It showed an open model can stand next to closed ones.
The foundation under most modern neural networks: GPU-accelerated tensors and automatic differentiation, wrapped in ordinary Python. Transformers, Llama and nearly every open model are written on it.