Vai al contenuto
TakoAPI
Torna alle skill

llmfit

di alexsjones

AI & LLMs
516Download riportati da clawskills.sh
1Visualizzazioni
0 likeAccedi per mettere like a questa skill
—Non ancora valutato
La tua valutazione

Sintesi

Detect local hardware (RAM, CPU, GPU/VRAM) and recommend the best-fit local LLM models with optimal quantization.

Descrizione

Cosa fa questa 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.

Quando 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

Esempio di workflow

INPUT

User asks: what local models can I run?

AGENT
  1. 1

    Run llmfit --json system to detect CPU, RAM, GPU name, and VRAM

  2. 2

    Run llmfit recommend --json --limit 5 to get top-scored models for the detected hardware

  3. 3

    Present each recommendation with fit level, best quantization, and estimated tokens/sec

  4. 4

    Map the chosen model's HuggingFace ID to its Ollama tag

  5. 5

    Update openclaw.json with the selected model and optionally set it as default

OUTPUT

Top 5 hardware-matched model recommendations with fit levels and quantization settings, plus an updated openclaw.json configuration

Requisiti

  • llmfit CLI — install via `brew tap AlexsJones/llmfit && brew install llmfit` or `cargo install llmfit`

Installazione

clawhub install alexsjones/llmfit

Esegui il comando CLI oppure incolla il prompt in Claude Code, Cursor, Codex o nell'agente di coding che usi.

Link