https://github.com/dorukgezici/pydantic-ai-mlx-lm

Add mlx-lm support to Pydantic AI, run MLX compatible HF models on Apple silicon.
https://github.com/dorukgezici/pydantic-ai-mlx-lm

mlx mlx-lm pydantic-ai

Last synced: 12 days ago
JSON representation

Add mlx-lm support to Pydantic AI, run MLX compatible HF models on Apple silicon.

• Host: GitHub
• URL: https://github.com/dorukgezici/pydantic-ai-mlx-lm
• Owner: dorukgezici
• Created: 2025-01-20T17:09:09.000Z (14 days ago)
• Default Branch: main
• Last Pushed: 2025-01-21T23:28:11.000Z (13 days ago)
• Last Synced: 2025-01-22T00:25:24.387Z (13 days ago)
• Topics: mlx, mlx-lm, pydantic-ai
• Language: Python
• Homepage: https://pypi.org/project/pydantic-ai-mlx-lm
• Size: 49.8 KB
• Stars: 0
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

        


	
pydantic-ai-mlx-lm

	
MLX local inference for Pydantic AI through mlx-lm

  






  

    

  

  

    

  



Run MLX compatible HuggingFace models on Apple silicon locally with Pydantic AI.

Still in development:

- [x] Non-streaming and streaming text requests

- [ ] Tool support

_Apple's MLX seems more performant on Apple Silicon than llama.cpp, which is what Ollama uses. (as of January 25)_

## Installation

```bash

uv add pydantic-ai-mlx-lm

```