TokenAssemble

Local LLM runtime

LM Studio

LM Studio is a proprietary-licensed local-LLM desktop app for Linux · macOS · Windows, running on CUDA · Metal · CPU · Vulkan · ROCm, with an OpenAI-compatible API. Ease of use 5/5 in our sourced ratings.

License
proprietary
Operating systems
Linux · macOS · Windows
Backends
CUDA · Metal · CPU · Vulkan · ROCm
Install
binary
Ease of use
5/5
Engine
llama.cpp|mlx

As of 2026-07-08 · source

Quant-format support

What the feasibility gate checks before any VRAM math — per format and backend.

FormatBackendSupported
ggufCPUyes
ggufCUDAyes
ggufMetalyes
ggufROCmyes
ggufVulkanyes
mlxMetalyes

Software that runs on LM Studio

Frontends, assistants and harnesses that can use LM Studio as their local backend.

Will your machine run a model with LM Studio?

Check with LM Studio preselected →

Support facts come from each runtime's own documentation, stamped and dated — how the math works.