oobabooga

Open-source desktop app for local LLMs. Text, vision, tool-calling, OpenAI/Anthropic-compatible API. 100% private.

No description.

Unsloth Studio is a web UI for training and running open models like Gemma 4, Qwen3.6, DeepSeek, gpt-oss locally.

Simplified installers for oobabooga/text-generation-webui.

4 bits quantization of LLaMa using GPTQ

No description.

Fast and memory-efficient exact attention - Windows wheels

Wheels for llama-cpp-python compiled with cuBLAS support

Easiest 1-click way to install and use Stable Diffusion on your computer. Provides a browser UI for generating images from text prompts and images. Just enter your text prompt, and see the generated image.

Various scripts for working with local LLMs

llama.cpp server in a Python wheel.

No description.

LLM Frontend for Power Users.

No description.

Large language models (LLMs) made easy, EasyLM is a one stop solution for pre-training, finetuning, evaluating and serving LLMs in JAX/Flax.

Stable Diffusion web UI

one-click deepfake (face swap)

🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.

Create UIs for your machine learning model in Python in 3 minutes

Running large language models on a single GPU for throughput-oriented scenarios.

A fast inference library for running LLMs locally on modern consumer-class GPUs

Create, edit and convert AI character files for CharacterAI, Pygmalion, Text Generation, KoboldAI and TavernAI

Python bindings for llama.cpp

No description.

An open source ChatGPT UI.

No description.

An extension to Oobabooga to add a simple memory function for chat

No description.

No description.

Code and documentation to train Stanford's Alpaca models, and generate the data.

Instruct-tuning LLaMA on consumer hardware

ChatRWKV is like ChatGPT but powered by RWKV (100% RNN) language model, and open source.

Windows compile of bitsandbytes for use in text-generation-webui.

Robust Speech Recognition via Large-Scale Weak Supervision

Stable Diffusion web UI

A simple batch file to make the oobabooga one click installer compatible with llama 4bit models and able to run on cuda

An easy-to-use LLMs quantization package with user-friendly apis, based on GPTQ algorithm.

No description.

Inference code for LLaMA models

🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.

A simple converter which converts pytorch bin files to safetensor, intended to be used for LLM conversion.

Port of Facebook's LLaMA model in C/C++

A combination of Oobabooga's fork and the main cuda branch of GPTQ-for-LLaMa in a package format.

AutoAWQ implements the AWQ algorithm for 4-bit quantization with a 2x speedup during inference. Documentation:

Code for the ICLR 2023 paper "GPTQ: Accurate Post-training Quantization of Generative Pretrained Transformers".

Merge Transformers language models by use of gradient parameters.

An optimized quantization and inference library for running LLMs locally on modern consumer-class GPUs

No description.

Create soft prompts for fairseq 13B dense, GPT-J-6B and GPT-Neo-2.7B for free in a Google Colab TPU instance

Discord bot for diffusers (Stable Diffusion)

Precompiled Wheels for GPTQ-for-LLaMa

Python bindings for llama.cpp

No description.

Utils for Unsloth https://github.com/unslothai/unsloth

No description.

No description.

No description.

8-bit CUDA functions for PyTorch

llama.cpp fork with additional SOTA quants and improved performance

css files created from pygment's built-in styles