Find the best local LLM for your hardware, ranked by benchmarks
LLM FrameworksA command‑line tool that auto‑detects your hardware and ranks the best local LLM from HuggingFace based on real benchmark scores.
Features
- Auto‑detects GPU/CPU/RAM and matches suitable models
- Ranks models using live benchmark data with confidence weighting
- One‑command chat (`whichllm run`) for instant inference
- Generates ready‑to‑use Python snippets (`whichllm snippet`)
- Simulates different GPUs before purchase (`--gpu "RTX 4090"`)
- Provides JSON output for script integration
Recent releases
View all 8 releases →Weekly OSS security release digest.
The CVE patches and breaking changes that affected production tools this week. One email, every Sunday.
No spam, unsubscribe anytime.
Install & Platforms
Install via
pip
brew
