LlamaChat

View on GitHub

View on Product Hunt

Chat with your favourite LLaMA models

LlamaChat allows you to chat with LLaMa, Alpaca and GPT4All models¹ all running locally on your Mac.

Alpaca
GPT4All
Vicuna Coming soon
LLaMA
Others

Alpaca is Stanford’s 7B-parameter LLaMA model fine-tuned on 52K instruction-following demonstrations generated from OpenAI’s text-davinci-003.

Fine-tuning the LLaMA model with these instructions allows for a chatbot-like experience, compared to the original LLaMA model.

GitHub | Paper

Convert models with ease

LlamaChat can import raw published PyTorch model checkpoints directly, or your pre-converted .ggml model files.

Fully open-source

LlamaChat is powered by open-source libraries including llama.cpp and llama.swift.

LlamaChat is 100% free and fully open-source, and always will be.

View on GitHub

See something missing? Open a Pull Request.

Download for Mac

$ brew install --cask llamachat

v1.2.0 | Built for Intel processors and Apple Silicon | Requires macOS 13

¹LLamaChat is not distributed with any model files, proprietary or otherwise. You are responsible for obtaining and integrating the appropriate model files in accordance with the respective terms and conditions set forth by their providers.

Disclaimer: LlamaChat is an independent application and is not affiliated with, endorsed by, or sponsored by Meta Platforms, Inc., Leland Stanford Junior University, or Nomic AI, Inc. The use of LlamaChat with artificial intelligence models or other intellectual property developed by these entities does not constitute any form of partnership or collaboration. All trademarks, service marks, and company names are the property of their respective owners.