Local AI

MLX

Apple's array framework for machine learning on Apple Silicon. Native Metal support, unified memory, first-class LLM inference.

Try MLXgithub.com/ml-explore/mlx

Save

MLX is Apple's machine learning framework built specifically for Apple Silicon. Unlike running llama.cpp through Metal, MLX is designed ground-up for the unified memory architecture of M-series chips, which means model weights and KV cache can be shared between CPU and GPU with no copy overhead. For local inference on a Mac, this delivers noticeably better tokens-per-second than the generic options at the same memory footprint. The ecosystem now includes mlx-lm for LLM inference with a simple Python API, mlx-vlm for vision-language models, and community-maintained quantized weights for most popular open-source LLMs. For anyone doing serious local work on a MacBook Pro or Mac Studio, MLX is the default inference layer in 2026.

apple-silicon metal local inference apple m-series

MLX at a glance

Last verified October 17, 2026

Pricing: Free and open source (MIT)
Install: pip install mlx
pip install mlx[cuda]
pip install mlx[cpu]
Models: MLX is an array framework, not a model runner. It runs on the Apple silicon CPU and GPU with unified memory, and it also has CUDA and CPU-only builds for Linux. LLM text generation and fine-tuning live in the companion mlx-lm package (pip install mlx-lm), which pulls models from the Hugging Face Hub.
Recent changes: Oct 14v0.32.4 adds VJPs for scaled dot product attention and gated delta net, Python 3.15 support, a fixed-size unique op and faster CUDA gather_qmm kernels, plus a long list of fixes.
Sep 29v0.32.3 adds Cholesky via cuSOLVER on CUDA, M5 Ultra tunings for non-quantized matmuls and a correction parameter for std and var.
Aug 25v0.32.2 adds a force_fused option to scaled_dot_product_attention and a fused full-attention path for head_dim 256 on NAX devices.

Sources: GitHub README, GitHub releases, mlx-lm README

Similar Tools

Local AI

llama.cpp

C++ inference engine for LLMs. GGUF format, quantization, CPU and Metal/CUDA support. The foundation most local tools build on.

Local AI

LM Studio

Desktop app for discovering, downloading, and running local LLMs. Clean chat UI, OpenAI-compatible API server, and automatic GPU detection. MLX engine optimized for Apple Silicon.

Local AI

vLLM

High-throughput inference server for LLMs. PagedAttention memory management. The go-to for serious local or self-hosted serving.

Local AI

Ollama

The easiest way to run LLMs locally. One command to pull and run any model. OpenAI-compatible API. 52M+ monthly downloads. Supports GGUF, Safetensors, and custom Modelfiles.

Get started with MLX

Apple's array framework for machine learning on Apple Silicon. Native Metal support, unified memory, first-class LLM inference.

Try MLX

Get weekly tool reviews

Honest takes on AI dev tools, frameworks, and infrastructure - delivered to your inbox.

Subscribe Free

Compare all pricing Compare side by side MLX-LM install, API and features

More Local AI Tools

Ollama

The easiest way to run LLMs locally. One command to pull and run any model. OpenAI-compatible API. 52M+ monthly downloads. Supports GGUF, Safetensors, and custom Modelfiles.

LM Studio

Desktop app for discovering, downloading, and running local LLMs. Clean chat UI, OpenAI-compatible API server, and automatic GPU detection. MLX engine optimized for Apple Silicon.

Jan

Open-source ChatGPT alternative that runs models fully offline. Desktop app with local models, cloud API connections, custom assistants, and MCP integration. Apache 2.0 licensed.