MLX LM
MIT Python package for text generation and fine-tuning of large language models on Apple silicon with MLX.
Tags
Description
Established open project (repo ml-explore/mlx-lm; not archived; created 2025-03-11; LICENSE Copyright © 2023 Apple Inc.; not presented as a 2026 launch). Root LICENSE is MIT. PyPI mlx-lm 0.32.2 (not yanked; uploaded 2026-10-16T02:49:33Z = 2026-10-16 03:49:33 Europe/Stockholm). GitHub latest release v0.32.2 was published 2026-10-16T02:49:02Z = 2026-10-16 03:49:02 Europe/Stockholm (not draft/prerelease). README install: pip install mlx-lm, or conda install -c conda-forge mlx-lm. Documented commands were not executed. README also describes Hugging Face Hub integration, quantization, LoRA and full fine-tuning (including quantized models), and distributed inference via mx.distributed. This is the mlx-lm package, not a separate listing of the broader MLX framework. Model weights are licensed separately. Apple silicon is the documented target.
Agent access
Related
- llama.cpp: MIT C/C++ library and server for local LLM inference, widely used as a local OpenAI-compatible backend for coding agents.
- Ollama: MIT app and API for running open models locally, plus a paid Ollama Cloud with usage credits and per-token prices.
- MLC LLM: Apache-2.0 compiler and deployment engine for running LLMs natively on NVIDIA, AMD, Apple, Intel, web, iOS and Android.
- vLLM: Apache-2.0 high-throughput LLM inference and serving engine with an OpenAI-compatible API, installable via uv or pip.
Sources
- https://github.com/ml-explore/mlx-lm
- https://github.com/ml-explore/mlx-lm/blob/main/LICENSE
- https://github.com/ml-explore/mlx-lm/blob/main/README.md
- https://github.com/ml-explore/mlx-lm/releases/tag/v0.32.2
- https://pypi.org/project/mlx-lm/
- https://pypi.org/project/mlx-lm/0.32.2/
Machine-readable
- JSON
- Markdown
- Source file on GitHub (edit via pull request)