The Local AI Leaderboard
Artificial Analysis ranks raw frontier intelligence - and almost all of it is proprietary, cloud-only, and metered by the token. We flip it: this board ranks the best models you can actually self-host, defaulting to open weights and surfacing the VRAM and params you need to run them. Same Intelligence / Coding / Math / Agentic indexes - reframed for $0/mo local instead of pay-per-call cloud.
Best you can run locally
GLM-5.2 leads the open field at 51.1 Intelligence - ~437 GB VRAM to run. Buy the GPU once, then $0/mo forever. No tokens, no rate limits, your data stays home.
Frontier, but cloud-only
Claude Fable 5 (with fallback) tops the proprietary board at 59.9 - but you can't download it. It's metered per token, can change or vanish overnight, and every prompt leaves your machine. Use the toggle below to compare it against what you can self-host.
Found a model that fits your GPU? Each one has a full page with benchmarks, VRAM math, and recommended hardware.
Browse all local models