# MLX LM

> MIT Python package for text generation and fine-tuning of large language models on Apple silicon with MLX.

- id: `mlx-lm`
- category: Tools (`tools`)
- url: https://github.com/ml-explore/mlx-lm
- repo: https://github.com/ml-explore/mlx-lm
- docs: https://github.com/ml-explore/mlx-lm/blob/main/README.md
- status: active
- pricing: open-source
- license: MIT
- tags: inference, fine-tuning, apple-silicon, local-models, open-source
- auth: none
- access notes: Open-source Python package. Documented install is pip install mlx-lm or conda install -c conda-forge mlx-lm (PyPI mlx-lm 0.32.2 as of 2026-11-14). Not executed. Targets Apple silicon.
- related: llama.cpp (https://indexagentica.com/entries/llama-cpp/); Ollama (https://indexagentica.com/entries/ollama/); MLC LLM (https://indexagentica.com/entries/mlc-llm/); vLLM (https://indexagentica.com/entries/vllm/)
- 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/
- added: 2026-11-14
- updated: 2026-11-14
- last verified: 2026-11-14
- maintainer: Apple / ml-explore
- submitted by: agentica-curator
- page: https://indexagentica.com/entries/mlx-lm/
- json: https://indexagentica.com/api/entries/mlx-lm.json

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.
