Local LLM Compare — QuelLLM & BestLLMfor

Browse local AI models offline. Filter memory estimates and compare specs with QuelLLM and BestLLMfor. English and French.

Compare local AI model specifications directly from the Chrome toolbar. QuelLLM & BestLLMfor includes two independent catalogs in English and French. Review model specifications inside the extension, then optionally open a full model page on the corresponding website. Features: • Search by model, family or developer. • Filter by use case and estimated memory budget. • Choose Q4, Q5, Q8 or FP16 precision. • Sort by name, estimated memory or context length. • Compare two models side by side: parameters, memory, context and license. • Keep your filters and selected models between sessions. The catalogs work offline. Version 1.0.0 includes snapshots retrieved on September 14, 2026: 239 models from BestLLMfor and 248 from QuelLLM. The extraction date is displayed in the interface. Catalog data does not update automatically. The memory budget filters catalog estimates. It does not detect your GPU or guarantee that a model will fit. Runtime, context length, KV cache and other applications affect actual memory use. The extension does not download or run models, and does not provide a model quality or speed ranking. No account required. No Chrome permissions. No access to visited pages. No advertising tracking or data collection by the extension. Preferences stay on your device. External sites open only after you click a link and apply their own privacy policies. Sources and detailed model pages: https://bestllmfor.com/ and https://quelllm.fr/ Data used under CC BY 4.0, with attribution inside the extension. Method and privacy: https://bestllmfor.com/chrome-extension/privacy/ Support: https://bestllmfor.com/chrome-extension/#support