llmfit
por alexsjones
AI & LLMsResumen
Detect local hardware (RAM, CPU, GPU/VRAM) and recommend the best-fit local LLM models with optimal quantization.
Descripción
Qué hace esta skill
Detects local hardware (CPU, RAM, GPU/VRAM) and ranks LLM models by how well they fit, with optimal quantization settings and estimated tokens-per-second. Each recommendation includes a composite score broken down by quality, speed, fit, and context length. Supports configuration for Ollama, vLLM, and LM Studio.
Instead of downloading a model and discovering it exceeds your VRAM at runtime, llmfit reads your actual hardware and scores candidates before you pull anything.
Cuándo usarla
- Checking which models fit your GPU before downloading from Ollama
- Finding the best coding model for a specific machine
- Confirming whether a large model like Llama 70B will run locally
- Choosing quantization level to maximize quality within VRAM limits
- Configuring LM Studio with hardware-matched model recommendations
Flujo de trabajo de ejemplo
User asks: what local models can I run?
- 1
Run
llmfit --json systemto detect CPU, RAM, GPU name, and VRAM - 2
Run
llmfit recommend --json --limit 5to get top-scored models for the detected hardware - 3
Present each recommendation with fit level, best quantization, and estimated tokens/sec
- 4
Map the chosen model's HuggingFace ID to its Ollama tag
- 5
Update openclaw.json with the selected model and optionally set it as default
Top 5 hardware-matched model recommendations with fit levels and quantization settings, plus an updated openclaw.json configuration
Requisitos
- llmfit CLI — install via `brew tap AlexsJones/llmfit && brew install llmfit` or `cargo install llmfit`
Instalación
clawhub install alexsjones/llmfitEjecuta el comando de la CLI o pega el prompt en Claude Code, Cursor, Codex o el agente de programación que uses.