# MTLDevice The main Metal interface to a GPU that apps use to draw graphics and run computations in parallel. ``` protocol MTLDevice : NSObjectProtocol, Sendable ``` ## Overview You can get the default [`MTLDevice`](/documentation/Metal/MTLDevice) at runtime by calling [`MTLCreateSystemDefaultDevice()`](/documentation/Metal/MTLCreateSystemDefaultDevice()) (see [Getting the default GPU](/documentation/Metal/getting-the-default-gpu)). Each Metal device instance represents a GPU and is the main starting point for your app’s interaction with it. With a Metal device instance, you can inspect a GPU’s features and capabilities (see [Device inspection](/documentation/Metal/device-inspection)) and create subsidiary type instances with its factory methods. - Buffers, textures, and other resources store, synchronize, and pass data between the GPU and CPU (see [Resource fundamentals](/documentation/Metal/resource-fundamentals)). - Input/Output command queues efficiently load resources from the file system (see [Resource loading](/documentation/Metal/resource-loading)). - Command queues create command encoders and schedule work for the GPU, including rendering and compute commands (see [Render passes](/documentation/Metal/render-passes) and [Compute passes](/documentation/Metal/compute-passes)). - Pipeline states store render or compute pipeline configurations — which can be expensive to create — so that you can reuse them, potentially many times. If your app uses more than one GPU (see [Multi-GPU systems](/documentation/Metal/multi-gpu-systems)), ensure that instances of these types only interact with others from the same device. For example, your app can pass a texture to a command encoder that comes from the same Metal device, but not to another device. ## Topics ### Working with GPU devices [Device inspection](/documentation/Metal/device-inspection) Locate and identify a GPU and the features it supports, and sample its counters. [Work submission](/documentation/Metal/work-submission) Create queues that submit work to the GPU or load assets into GPU resources, and indirect command buffers that group your frequent commands together. [Pipeline state creation](/documentation/Metal/pipeline-state-creation) Create pipeline states for render and compute passes, samplers, depth and stencil states, and indirect command buffers. [Resource creation](/documentation/Metal/resource-creation) Load assets with input/output queues and make various resource instances, such as buffers, textures, acceleration structures, and memory heaps. [Shader library and archive creation](/documentation/Metal/shader-library-and-archive-creation) Create static and dynamic shader libraries, and binary shader archives. --- Copyright © 2026 Apple Inc. All rights reserved. | [Terms of Use](https://www.apple.com/legal/internet-services/terms/site.html) | [Privacy Policy](https://www.apple.com/privacy/privacy-policy)