Local inference
MLX
Apple’s array framework for Apple silicon, with a growing set of ready-to-run model ports.
- Category
- Local inference
- Pricing
- Open source
- Runs
- Runs locally
- Languages
- Python, C++, Swift
- Interface
- Library
- Source
- Open source
What MLX is
MLX is Apple's array framework built for Apple silicon's unified memory, where CPU and GPU share the same pool and large models fit without a dedicated graphics card. The mlx-lm companion provides ready-to-run ports of many open-weight models, and it supports fine-tuning locally as well as inference.
Best for
Getting the most out of a Mac, and local fine-tuning on Apple silicon.
Consider something else if
Apple silicon only — there is no path to other hardware.
MLX alternatives
The closest options in local inference, on the axes that actually separate them.
| Tool | Best for | Pricing | Runs |
|---|---|---|---|
| MLXopen source | Getting the most out of a Mac, and local fine-tuning on Apple silicon. | Open source | Runs locally |
| llama.cppopen source | Squeezing a model onto constrained hardware, and embedding inference into your own application. | Open source | Runs locally |
| Ollamaopen source | Anyone trying local inference for the first time, and for local development against a model that costs nothing per call. | Open source | Runs locally |
| LM Studio | Running models locally without the terminal, and comparing several quickly in one interface. | Free tier | Runs locally |
| vLLMopen source | Serving an open-weight model to real traffic on GPUs you operate. | Open source | Self-hosted |
Choosing within local inference
One user or many
Single-user tools optimise for a fast start and easy model switching. Serving engines optimise throughput across concurrent requests via batching. Using the first for a production endpoint wastes most of your GPU.
Your hardware
Apple silicon, NVIDIA, and CPU-only are genuinely different targets. Some tools cover all three; others are built for one and are much faster on it.
Questions
What is MLX?
MLX is Apple's array framework built for Apple silicon's unified memory, where CPU and GPU share the same pool and large models fit without a dedicated graphics card. The mlx-lm companion provides ready-to-run ports of many open-weight models, and it supports fine-tuning locally as well as inference. It is open source and runs locally.
What are the alternatives to MLX?
The closest alternatives are llama.cpp, Ollama, LM Studio, vLLM. They sit in the same category — local inference — and differ mainly on hosting model, pricing shape, and how much they abstract away.
Is MLX the right choice?
Getting the most out of a Mac, and local fine-tuning on Apple silicon. The main caveat: Apple silicon only — there is no path to other hardware.
Whatever you build on, the model is the line item that scales. See what each one costs per million tokens, or price your own workload.