Pavelevich/llm-checker
Advanced CLI tool that scans your hardware and tells you exactly which LLM or sLLM models you can run locally, with full Ollama integration.
Performs deterministic multi-dimensional scoring (Quality, Speed, Fit, Context) across 200+ dynamically-scraped Ollama model variants with hardware-calibrated memory estimation validated against real quantizations. Pure JavaScript with optional SQLite search, supports Apple Silicon, NVIDIA CUDA, AMD ROCm, and Intel Arc GPU detection, enabling calibrated routing policies for repeatable model selection across different use cases and hardware configurations.
1,642 stars. Actively maintained with 23 commits in the last 30 days. Available on npm.
Stars
1,642
Forks
105
Language
JavaScript
License
—
Category
Last pushed
Mar 14, 2026
Commits (30d)
23
Dependencies
10
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/llm-tools/Pavelevich/llm-checker"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.