Llmfit
FreeHundreds of models & providers. One command to find what runs on your hardware.
FreeFree tier
About Llmfit
Llmfit is a terminal tool that right-sizes LLM models to your system's RAM, CPU, and GPU. It detects your hardware, scores each model across quality, speed, fit, and context dimensions, and tells you which ones will actually run well on your machine. Ships with an interactive TUI (default) and a classic CLI mode. Supports multi-GPU setups, MoE architectures, dynamic quantization selection, speed estimation, and local runtime providers (Ollama, llama.cpp, MLX, Docker Model Runner, LM Studio). Includes a benchmark share feature that lets you download a model, serve it, and measure real tok/s on your hardware, contributing results back to the project.
Key Features
Detects system hardware (RAM, CPU, GPU) to estimate model fit
Scores models across quality, speed, fit, and context dimensions
Interactive TUI and classic CLI modes
Supports multi-GPU setups and MoE architectures
Dynamic quantization selection based on hardware
Speed estimation without running the model
Benchmark share feature for measuring real tok/s and contributing results
Local runtime providers: Ollama, llama.cpp, MLX, Docker Model Runner, LM Studio
Cross-platform installation via Homebrew, Scoop, MacPorts, or quick install script
Pros & Cons
Pros
- Free and open source under MIT license
- Hardware-aware model selection saves time and prevents incompatibility
- Supports multiple runtime providers for flexibility
- Interactive TUI and CLI cater to different user preferences
- Benchmark sharing improves estimates for the entire community
- Cross-platform with easy installation on Windows, macOS, and Linux
Cons
- Requires some technical knowledge to install and operate
- Only works with supported runtime providers (Ollama, llama.cpp, MLX, etc.)
- Model database may not include every available LLM
- Performance estimates without running a benchmark are approximate
Best For
Finding LLMs that run efficiently on specific hardware configurationsBenchmarking and comparing model performance on local machinesSelecting appropriate quantization and runtime for deploymentAutomating model selection in scripts or pipelines using CLIContributing performance data to the community through benchmark sharing
FAQ
How do I install llmfit?
Installation is available via Homebrew on macOS/Linux (brew install AlexsJones/llmfit/llmfit), Scoop on Windows (scoop install llmfit), MacPorts (port install llmfit), or a quick install script (curl -fsSL https://llmfit.axjns.dev/install.sh | sh).
What is the benchmark share feature?
The benchmark share feature allows you to download a model, serve it, and measure real tok/s on your machine. Results are saved locally and can be contributed to the project as a pull request directly from the TUI. Merged submissions ship in the next release, giving others on identical hardware verified numbers before they run their own benchmarks.
Which runtime providers are supported?
Llmfit supports local runtime providers including Ollama, llama.cpp, MLX, Docker Model Runner, and LM Studio.