MLX
Apple’s array framework for running and fine-tuning models on Apple silicon.
An open-source machine-learning framework for Apple silicon with unified memory; its MLX-LM package runs and fine-tunes open LLMs locally on a Mac and powers many local-AI apps.
- Vendor
- Apple
- Category
- Inference & model hosting
- Pricing
- Open source
- Open source
- Yes
- License
- MIT
- Platforms
- macOS, Python, Swift
- Launched
- 2023
- Website
- ml-explore.github.io/mlx
Features
- Apple silicon acceleration
- MLX-LM inference
- LoRA fine-tuning
Best for
- Local & on-device
More inference & model hosting
- Ollama — Ollama. Run open models locally with one command.
- vLLM — vLLM project. High-throughput LLM serving engine.
- llama.cpp — ggml. LLM inference in C/C++ on any hardware.
- Amazon Bedrock — AWS. Foundation models on AWS.
- Vertex AI — Google Cloud. Google Cloud’s AI platform.
- LM Studio — Element Labs. Desktop app to discover and run local LLMs.
- Azure AI Foundry — Microsoft. Build and run AI apps on Azure.
- Groq — Groq. Ultra-fast inference on custom LPUs.