Skip to content

alt.freeweights.tools / mlx-lm

From:

ml-explore <github.com/ml-explore>Newsgroups: alt.freeweights.toolsSubject:

mlx-lm

Release: v0.32.2 (2026-10-16)Commit: 93e6d4aLicense: MIT

Run and fine-tune language models on Apple silicon with MLX.

inference engine

v0.32.2releasemlx-lmPythonMIT

FactsLicenseMITLanguagePythonKindinference engineRelease2026-10-16PlatformsmacOS (Apple silicon)Links to the projectpermissive

$ pip install mlx-lm
# use with Freeweights
$ mlx_lm.generate --model <id> --prompt "Hello"

Overview Install Use with Freeweights License Provenance

Overview

Run and fine-tune language models on Apple silicon with MLX.

Kind: inference engine
License: MIT
Language: Python
Platforms: macOS (Apple silicon)
Latest release: v0.32.2 (2026-10-16)
Repository: ml-explore/mlx-lm

Topicsllmsmlx

Freeweights links to the project and does not host tool binaries.

Install

$ pip install mlx-lm
# use with Freeweights
$ mlx_lm.generate --model <id> --prompt "Hello"

$ pip install mlx-lm

Checked against the project's README on 2026-11-14. The project's own instructions win when they differ: install docs

Freeweights links to the project and does not host tool binaries.

Use with Freeweights

Run a catalog model

$ mlx_lm.generate --model <id> --prompt "Hello"

Download the weights from Freeweights first (HF_ENDPOINT or fw.py), then point the tool at the folder.

Catalog models it can run (207)

distilled_decoding kitten-tts-micro-0.8 kitten-tts-mini-0.8 kitten-tts-nano-0.1 kitten-tts-nano-0.8-fp32 mri-autoencoder-v0.1 MS-Human-700 UltraData-Code-L2-Classifier videoprism-large-f8r288 videoprism-lvt-base-f16r288 whisper-large-v3-mlx Codestral-22B-v0.1-4bit cxr-foundation DeepSeek-Coder-V2-Instruct-AQ4_1 DeepSeek-Coder-V2-Lite-Instruct-4bit DeepSeek-Coder-V2-Lite-Instruct-4bit-mlx DeepSeek-Coder-V2-Lite-Instruct-8bit DeepSeek-V3-0324-4bit DeepSeek-V3-4bit derm-foundation dolphin-2.9-llama3-70b-4bit Dolphin3.0-Llama3.1-8B-MLX-4bit dolphin3.0-llama3.2-1B-4Bit dolphin3.0-llama3.2-3B-4Bit encodec-24khz-float32 FastVLM-0.5B-bf16 functiongemma-270m-it-4bit gemma-3-1b-it-4bit-DWQ gemma-3-270m-it-4bit gemma-3-270m-it-8bit gemma-3n-E2B-it-lm-4bit gemma-3n-E4B-it-lm-4bit gemma-4-12B-it-OptiQ-4bit gemma-4-12B-it-qat-assistant-4bit gemma-4-26b-a4b-4bit gemma-4-26B-A4B-it-assistant-bf16 gemma-4-26B-A4B-it-OptiQ-4bit gemma-4-26B-A4B-it-OptiQ-4bit-REAP-14B gemma-4-26B-A4B-it-qat-assistant-4bit gemma-4-31b-8bit gemma-4-31b-bf16 gemma-4-31B-it-assistant-bf16 gemma-4-31B-it-OptiQ-4bit gemma-4-e2b-4bit gemma-4-e2b-it-4bit gemma-4-e2b-it-8bit gemma-4-E2B-it-assistant-bf16 gemma-4-e2b-it-bf16 gemma-4-e2b-it-OptiQ-4bit gemma-4-e2b-it-OptiQ-4bit-decision gemma-4-e4b-4bit gemma-4-e4b-it-4bit gemma-4-e4b-it-6bit gemma-4-e4b-it-8bit gemma-4-E4B-it-assistant-bf16 gemma-4-e4b-it-bf16 gemma-4-e4b-it-OptiQ-4bit gemma-4-E4B-it-qat-assistant-4bit GLM-4.7-REAP-50-mxfp4 GLM-5.3-4bit

and 147 more.

License

License: MIT
Class: Permissive

Read the license

Freeweights links to the project and does not host tool binaries.

Provenance

From:

ml-explore <github.com/ml-explore>Newsgroups: alt.freeweights.toolsSubject: mlx-lmRelease: v0.32.2 (2026-10-16)Commit: 93e6d4aLicense: MIT

Repository: ml-explore/mlx-lm
Pinned release: v0.32.2, 2026-10-16
Release commit: 93e6d4a6447b3080861985947f0820e76fcb957d
Default branch: main 56230fa02b8ff8330daf26dc95c28480423ed5fe
Fetched: 2026-11-14
Takedowns: None.

Freeweights links to the project and does not host tool binaries.

Get it

Install Project repository

Works with

207 catalog models. See the list