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
- Graphical app (GUI)
- Server mode
- OpenAI-compatible API
- CPU offload
- Multi-GPU
- Speculative decoding
- LoRA support
- KV-cache quantization
- One-line install
As of 2026-07-08 · source
Quant-format support
What the feasibility gate checks before any VRAM math — per format and backend.
| Format | Backend | Supported |
|---|---|---|
| gguf | CPU | yes |
| gguf | CUDA | yes |
| gguf | Metal | yes |
| gguf | ROCm | yes |
| gguf | Vulkan | yes |
| mlx | Metal | yes |
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.