Local inference

MLX

Apple’s array framework for Apple silicon, with a growing set of ready-to-run model ports.

Visit github.com ↗

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.

MLX compared with 4 alternatives
ToolBest forPricingRuns
MLXopen sourceGetting the most out of a Mac, and local fine-tuning on Apple silicon.Open sourceRuns locally
llama.cppopen sourceSqueezing a model onto constrained hardware, and embedding inference into your own application.Open sourceRuns locally
Ollamaopen sourceAnyone trying local inference for the first time, and for local development against a model that costs nothing per call.Open sourceRuns locally
LM StudioRunning models locally without the terminal, and comparing several quickly in one interface.Free tierRuns locally
vLLMopen sourceServing an open-weight model to real traffic on GPUs you operate.Open sourceSelf-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.

The full guide to local inference →

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.