AlexsJones/llmfit

Health v2 · maintenance only

Adoption not part of the score

34236 stars · 2139 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-29, confidence not recorded

llmfit is a Rust-based terminal tool (TUI and CLI) that matches LLM models to your hardware by detecting RAM, CPU, and GPU and scoring models on quality, speed, fit, and context. It supports hundreds of models and providers, multi-GPU setups, MoE architectures, quantization selection, speed estimation, and community benchmark contributions.

Use cases

• find which LLM models run on my hardware
• check if a GGUF model fits in my RAM
• recommend local LLM for my GPU
• estimate tokens per second for a model on my machine
• compare model quality vs speed for local inference
• pick the right quantization for my VRAM

When to choose

• you run local LLMs with Ollama, llama.cpp, MLX, or LM Studio and want to know what fits
• you want hardware-aware model recommendations with speed and quality scoring
• you prefer an interactive TUI plus scriptable CLI in one tool

When to avoid

• you need to actually serve or chat with models rather than select them
• you only use cloud APIs and never run models locally
• you need GPU cluster-scale inference scheduling

Facets

cli-tool · maturity active

llm-inference benchmarking cli terminal-ui developer-tools large-language-models developer-tools machine-learning windows cli rust gguf local-llm hardware-detection model-selection tui ollama llama-cpp mlx command-line linux macos

Member repositories

For agents

markdown · JSON · MCP: product_card(name="AlexsJones/llmfit")