Tools · SPBoucher
Menu

Metal

by Apple Inc. · Framework · also known as Apple Metal, Metal Performance Shaders

Apple's low-level GPU programming framework for graphics and parallel compute on iOS, macOS and visionOS, the layer beneath MLX, Core ML and most Apple Silicon ML runtimes

ProprietaryFreeLocal
Visit official site Compare

Link verified Nov 2, 2026

Overview

Metal is Apple's low-overhead API for programming the GPU on its devices, introduced in 2014 and now the only supported graphics and compute interface on Apple platforms. Developers write shaders and compute kernels in the Metal Shading Language, a C++-derived dialect, and submit command buffers that the framework schedules on the GPU. Companion libraries include Metal Performance Shaders (optimized kernels for image processing, linear algebra and neural-network layers), MetalFX upscaling and MetalKit for display plumbing.

For machine learning on Apple Silicon, Metal is the foundation rather than the tool most people touch directly: MLX, PyTorch's MPS backend, llama.cpp, Core ML and the Foundation Models framework all dispatch their GPU work through it, and the unified memory architecture of M-series chips lets those frameworks share buffers between CPU and GPU without copies. Developers reach for Metal itself when they need custom kernels, graphics rendering or profiling with Xcode's GPU tools.

It is proprietary and Apple-only; there is no Linux, Windows or Android target, so portable GPU code usually goes through Vulkan, WebGPU or a framework that abstracts the backend.

Capabilities

  • Low-level GPU command submission for graphics and compute
  • Metal Shading Language for shaders and compute kernels
  • Metal Performance Shaders for image, linear-algebra and neural-network kernels
  • GPU debugging and profiling in Xcode
  • Unified-memory buffer sharing on Apple Silicon

Typical workflows

  1. Write a custom compute kernel for a scientific application
  2. Profile the GPU work of an MLX or PyTorch program
  3. Render 3D content in a native macOS app

Strengths

  • Direct access to Apple GPUs with minimal driver overhead
  • Underpins every ML framework on Apple Silicon
  • First-class tooling in Xcode

Limitations

  • Apple platforms only
  • Steep learning curve compared with high-level frameworks
  • No portability to Linux or Windows GPUs

Prerequisites

  • Xcode on macOS
  • Swift, Objective-C or C++

Who it is for

  • Graphics and game developers
  • ML framework and kernel authors on Apple Silicon

Alternatives & comparison

  • JAX

    Python library for NumPy-style array computing with composable transformations (jit, grad, vmap, shard_map) compiled through XLA to CPU, GPU and TPU

    Open sourceOpen source
  • MLX

    Apple's open-source array framework for machine learning on Apple Silicon, with NumPy-like Python, C++ and Swift APIs and unified CPU/GPU memory

    Open sourceOpen source
  • PyTorch

    Open-source deep-learning framework with eager tensors, autograd, torch.compile and distributed training, governed by the PyTorch Foundation and the base of most LLM tooling

    Open sourceOpen source
Compare Metal with its alternatives →

Sources & verification

Primary sources consulted for this record. Claims are tied to the fields each source supports; the automated link checker re-verifies every URL on a schedule.

Confidence
High
Reviewed
Nov 1, 2026
Links
Verified · Nov 2, 2026

Spotted an error?

Broken link, outdated license, wrong category, or a tool that no longer exists? Tell us; reports are reviewed by the editor.

llama.cpp

ggml-org (Georgi Gerganov and contributors) · Local LLM inference & serving

In-depth entry

C/C++ inference engine for LLMs and vision-language models with GGUF quantized weights, Metal, CUDA, Vulkan and other backends, a CLI and an OpenAI-compatible server

MITOpen sourceFreeLocalSelf-hostedNov 2, 2026

LM Studio

Element Labs, Inc. · Local LLM inference & serving

In-depth entry

Proprietary desktop app for discovering, downloading and running local LLMs with llama.cpp and MLX engines, a chat UI, an OpenAI-compatible server, CLI, SDKs and a headless daemon

ProprietaryFreemiumPaidLocalBroken

MLX LM

Apple Inc. · Apple Silicon ML & MLX

In-depth entry

Python package and CLI for running, serving, quantizing and fine-tuning large language models on Apple Silicon with MLX

MITOpen sourceFreeLocalNov 2, 2026

Ollama

Ollama · Local LLM inference & serving

In-depth entry

Open-source runtime and model manager for running open-weight LLMs locally on macOS, Windows and Linux, with a REST API, OpenAI- and Anthropic-compatible endpoints and optional cloud models

MITOpen sourceFreeLocalSelf-hostedNov 2, 2026

Core ML

Apple Inc. · Apple Silicon ML & MLX

Apple's on-device machine-learning runtime for iOS and macOS apps, with the open-source coremltools package for converting PyTorch and other models to its format

BSD-3-ClauseFreeLocalNov 2, 2026

Create ML

Apple Inc. · Apple Silicon ML & MLX

Apple's app and Swift framework for training image, text, sound, tabular and activity models on a Mac without writing training code, exporting directly to Core ML

ProprietaryFreeLocalNov 2, 2026