Local AI on macOS

Written by Jakub Rusinowski · Last updated July 12, 2026

Unified memory lets a Mac load models far larger than any consumer GPU can hold, at a fraction of the memory bandwidth — capacity you can buy, speed you cannot.

Runtimes that work on macOS

Runtime	How to install	Acceleration	Watch out for
Ollama	Official macOS app, or Homebrew. brew install ollama	Metal (Apple Silicon)	—
LM Studio	Official macOS app; ships both the Metal and MLX runtimes.	Metal, MLX	—
MLX	Apple's own array framework, installed via pip. pip install mlx-lm	Metal (Apple Silicon)	Usually the fastest option on Apple Silicon, but needs MLX-format weights — not every model has an MLX conversion.
llama.cpp	Homebrew, or build from source (Metal is enabled by default on Apple Silicon). brew install llama.cpp	Metal, CPU	—

What macOS is good at

• The cheapest way to get 64–256 GB of accelerator-addressable memory in one box.
• Very low idle power and near-silent operation, which makes an always-on local assistant practical.
• MLX gives Apple Silicon a first-party, actively developed inference path.

macOS limitations

• macOS caps how much unified memory the GPU may claim; the default ceiling is roughly 75% of total memory, which is why usable figures on this site are below the sticker capacity.
• Memory is soldered on every Apple Silicon Mac — the configuration you buy is permanent, so buy the memory you will need later.
• Memory bandwidth is well below a discrete GPU at the same price: a Mac that loads a 70B model still generates far slower than a GPU that can hold it.
• No CUDA, so tooling that assumes CUDA — including most fine-tuning stacks — will not run.

Hardware and models on macOS

macOS supports Apple accelerators — 18 of the 55 in our hardware database, up to 512 GB.

Memory	Hardware on this platform	Models to run
8 GB	—	Qwen 3 8B GLM-6 9B GLM-4.7 9B
16 GB	Apple M1	Mistral Small 3.1 24B Qwen 3.5 14B Qwen 3.5 14B
24 GB	Apple M4 Pro Apple M2 Apple M3	Gemma 4 27B ⭐ Mistral Small 3.1 24B Qwen 3.7 35B-A3B
48 GB	—	Nemotron 70B Instruct GLM-5.1 72B Qwen 3.5 72B
96 GB	Apple M2 Max	GPT-oss 120B Nemotron 70B Instruct Qwen 3.5 122B-A10B (MoE)
192 GB	Apple M2 Ultra	Qwen 3 235B-A22B (MoE) DeepSeek V4.1 Flash DeepSeek V4-Flash

Machines that run macOS

Machine	Memory for models	Form factor	Upgradeable
MacBook Pro 16" (M4 Max, 128 GB)	128 GB unified	Laptop	No
MacBook Pro 16" (M4 Max, 48 GB)	48 GB unified	Laptop	No
Mac Studio (M3 Ultra, 256 GB)	256 GB unified	Desktop	No
MacBook Pro 14" (M4 Pro, 24 GB)	24 GB unified	Laptop	No
Mac Studio (M4 Max, 64 GB)	64 GB unified	Desktop	No
MacBook Air (M4, 16 GB)	16 GB unified	Laptop	No
Mac mini (M4, 16 GB)	16 GB unified	Mini PC	No
MacBook Pro 16" (M5 Max, 128 GB)	128 GB unified	Laptop	No

FAQ

What is the best way to run an LLM locally on macOS?

Ollama — Official macOS app, or Homebrew. It reaches Metal (Apple Silicon).

Which GPUs work for local AI on macOS?

Apple hardware, up to 512 GB in our database.

What are the downsides of running local AI on macOS?

macOS caps how much unified memory the GPU may claim; the default ceiling is roughly 75% of total memory, which is why usable figures on this site are below the sticker capacity.

Machines Running This Platform

• Run BitNet b1.58 on MacBook Pro M4 Max 128 GB
• Run BitNet b1.58 on MacBook Pro M4 Max 48 GB
• Run BitNet b1.58 on Mac Studio M3 Ultra 256 GB
• Run BitNet b1.58 on MacBook Pro M4 Pro 24 GB

Hardware for This Platform

• Best models for the Apple M3 Ultra
• Best models for the Apple M2 Ultra
• Best models for the Apple M4 Max
• Best models for the Apple M1 Ultra

Other Platforms

• Local AI on Windows
• Local AI on Linux

Tools

• Best local LLMs to start with
• Check your own hardware
• Can I run it?

← All platforms | Check your hardware