kitio.aiAdded Oct 28, 2026
MLX
FreeApple's array framework for running and training models on Apple Silicon
What is MLX?
MLX is an open-source machine learning framework from Apple designed for Apple Silicon, using unified memory to run and fine-tune models on Macs. Its companion package mlx-lm makes it easy to run and fine-tune open language models locally.
MLX has a NumPy-like Python API plus Swift and C++ bindings, lazy computation and automatic differentiation. Because CPU and GPU share memory, Macs with large RAM can run models that would not fit on many consumer GPUs.
The community publishes thousands of MLX-converted models on Hugging Face, and LM Studio can run MLX models directly. It is free under the MIT license and developed in the open.
Features
- Unified memory use
- NumPy-like API
- mlx-lm for LLMs
- LoRA fine-tuning
- Swift bindings
Tags
Releases
+ Submit new release- Listed
MLX was added to the directory.
Organization
Apple
🇺🇸 United States
Listed by kitio.ai · unverified owner
Pricing
- Pricing model
- Free
- Paid options from
- 100% free
Sponsored
Your AI tool here
A Featured launch puts your tool in this spot and on the home page for a week.
Top MLX alternatives
View allModels & APIs
Run open models locally with one command, plus optional cloud models
Models & APIs
Open-source deep learning library that runs on JAX, PyTorch and TF
Models & APIs
Gradio web interface for running local LLMs with many backends
If you liked MLX
Package an LLM and its runtime into one portable executable file
FreeModels & APIsMade in United States
Pros and cons
Pros
- Fast on Apple Silicon
- Runs big models on high-RAM Macs
- Simple Python API
Cons
- Mac only
- Smaller ecosystem than PyTorch
- Some models need conversion
Prompts & results
No prompts yet. Add your own prompt and output to help others use this tool.
Share a prompt
Reviews
Q&A
What is MLX?
MLX is an open-source machine learning framework from Apple designed for Apple Silicon, using unified memory to run and fine-tune models on Macs. Its companion package mlx-lm makes it easy to run and fine-tune open language models locally.
How much does MLX cost?
MLX is 100% free.
Is there a free version of MLX?
Yes. MLX is completely free to use.
What are the main features of MLX?
Unified memory use, NumPy-like API, mlx-lm for LLMs, LoRA fine-tuning, Swift bindings.
Who makes MLX?
MLX is made by Apple.
What are the best alternatives to MLX?
Popular alternatives include Ollama, llama.cpp, Keras.