MLX LM
A Python package and command-line tool for running and fine-tuning language models on Apple silicon.
These buttons open the developer's own site, repository or store listing in a new tab. wares.gg does not host downloads.
1 more ways to get MLX LM
Package managers
- Homebrew
brew install mlx-lm
About MLX LM
MLX LM generates text with large language models and fine-tunes them on Apple silicon Macs, using the MLX array framework. It integrates with the Hugging Face Hub, so thousands of models can be downloaded and run with a single command.
It can also quantize models and upload them back to the Hub. It suits developers and technically minded Mac users who are comfortable with Python and the terminal. It does not offer a graphical chat application.
Strengths
- Runs models on Apple silicon through MLX
- One-command access to models on the Hugging Face Hub
- Supports fine-tuning and quantization as well as generation
Limitations
- Apple silicon only
- Command line and Python, with no graphical interface
- License not confirmed in the research
Details
- Pricing
- FreeFree to install and use.
- License
- Proprietary
- Developer
- ml-explore
- Platforms
- macOS, Command line
- How it runs
- Downloadable app
- Best suited for
- Mac users with Apple silicon who want to run or fine-tune LLMs from the terminal
- Categories
- Local AI tools, Developer tools
- Last verified
- Added
- Provenance
- Facts checked against the developer's own pages and store listings, 1 sources on file.
Alternatives to MLX LM
Compare allSoftware that can replace MLX LM for an important use case, and what changes if you switch.
llama.cpp
The C++ engine most local AI apps are built on, running language models on ordinary hardware.
llama.cpp is MIT licensed and runs across Windows, macOS, Linux and Android with many GPU backends, but lacks MLX LM's fine-tuning.
Unsloth
A local interface and command-line tool for running and fine-tuning language and diffusion models.
Unsloth runs and fine-tunes models on Windows, macOS and Linux with a local UI and supports MLX and GGUF formats.
Ollama
The simplest way to pull down an open language model and run it on your own machine, from one command or a desktop app.
Ollama is MIT licensed, runs models with one command on all desktop platforms and exposes a local REST API, without fine-tuning.
LM Studio
A polished desktop app for downloading, running and chatting with local language models, with an OpenAI-compatible server built in.
LM Studio wraps MLX and llama.cpp in a closed source desktop GUI with an OpenAI-compatible server and an lms command line tool.
LLM
A command-line tool and Python library for prompting remote and locally installed language models.
LLM is a command-line tool and Python library for prompting remote and local models with SQLite logging, but local models need a plugin.
MLX LM as an alternative
Listings that name MLX LM as an alternative.
Axolotl
A command-line tool for fine-tuning language models from YAML configuration files.
MLX LM fine-tunes and quantizes models on Apple silicon Macs instead of Linux GPUs, and its license is not confirmed.
Similar software
Related functionality, not necessarily a direct replacement.
LlamaFactory
Web UI and command-line toolkit for fine-tuning over 100 open language and vision-language models.
LLMFarm
An iOS and macOS app for running large language models offline on the device using GGML.
Private LLM
An offline AI chat app for iPhone, iPad and Mac that runs open language models on the device.
