llmfit detects your hardware, including Apple silicon unified memory, and scores open models on quality, speed, fit and context so you can see which ones your machine can run and at what quantisation. It has an interactive terminal UI, a classic CLI mode, a web dashboard and a small REST API.
It works with local runtimes such as Ollama, llama.cpp, MLX, Docker Model Runner and LM Studio, and can download a model, serve it and measure real tokens per second. You can choose to send the benchmark results back to the project.
It runs on macOS (Apple silicon and Intel), Linux and Windows. It's free and open source (MIT).
How to Get It
brew install llmfitcurl -fsSL https://llmfit.axjns.dev/install.sh | shOfficial downloads only. MLX never re-hosts an app, and never runs a command for you.
MLX Score
Ranked against the developer tools listings, from real public data only. How the score works.
Pairs Well With
OllamaRun locally
LM StudioRun locallyInformation
- Developer
- Alex Jones
- Category
- Developer tools
- Price
- Free
- Your data
- Runs on your Mac
- Licence
- MIT
- Mac
- Runs on a Mac (no minimum stated)
- iPhone and iPad
- —
- Facts checked
- 2026-11-03
Sources
You Might Also Like
uvDev tools
TransformersDev tools
LiteLLMDev tools
Hugging Face CLI (hf)Dev tools
MLX-TuneDev tools
Foundation Models SDK for PythonDev toolsllmfit is a product of Alex Jones; MLX isn’t affiliated with it. Something wrong? Write to support@mlx.app.