AlexsJones/llmfit

Project overview

llmfit detects local RAM, CPU, and GPU/VRAM resources and scores LLM models across memory fit, speed, quality, and context dimensions to recommend matches for specific hardware. It runs as a local CLI or interactive TUI and supports benchmarking against running inference providers.

Project type

Model Runtime

Deployment

Refer to project documentation

License

MIT

Best for

• Developers, AI engineers, and general users who need to identify which LLMs will run locally given their specific RAM, CPU, and GPU constraints.
• Automation workflows that require machine-readable JSON output for programmatic model selection.

Key capabilities

• Detects system RAM, CPU, GPU/VRAM, and backend to determine available compute resources.
• Scores every model in its catalog across four dimensions: memory fit, estimated speed, quality, and context.
• Ships with an interactive Terminal User Interface (TUI) as the default mode for exploring hardware specs and model scores.
• Provides classic terminal commands and JSON output for scripts, agents, and automation.
• Measures real tok/s and TTFT against a running provider, allowing users to share results back to the project via a PR.

Limitations and risks

• The project runs locally and is self-hosted; no managed service deployment option is available.
• Minimum hardware requirements are not provided, though the application's purpose is to evaluate fit against whatever local hardware is present.

Getting started

• Install the application via a single command using major package managers such as Homebrew, Scoop, MacPorts, pip, or Docker, then run llmfit in the terminal.

Evidence and sources

• README: A terminal tool that right-sizes LLM models to your system's RAM, CPU, and GPU. Detects your hardware, scores each model across quality, speed, fit, and context dimensions, and te…
• README: `llmfit bench --share` measures real tok/s on your hardware and contributes it back to the project as a PR — no `gh` CLI, no third-party account.
• GitHub project description: Hundreds of models & providers. One command to find what runs on your hardware.
• README: scoop install llmfit
• README: brew install AlexsJones/llmfit/llmfit

Reviewed at: 2026-07-17T09:46:22Z