whatmodel: open-source tool matches local AI models to your RAM and GPU from 22k benchmarks
JeremyCMorgan · x · 2026-10-22
Developer Jake Manger released whatmodel, an open-source (MIT) tool that recommends the best AI models you can run locally based on your RAM and GPU, covering LLMs, image/video generation, and speech models. It draws on over 22,000 benchmark results and links to the scores behind each rank — worth a check before buying another GPU.
More from Infra
- Open tool computes API vs. RunPod self-hosting breakeven across 450+ models, with VRAM sizing — zackku · 2026-10-22
- Railway breach timeline: crypto theft began 2 hours before users were told to rotate keys — banteg · 2026-10-22
- SemiAnalysis deep-dive: Huawei Ascend 950PR hits 86% median MFU, beating all Nvidia chips, but only A100-tier compute — teortaxesTex · 2026-10-22
- NVIDIA shows off DGX Spark clusters, Vera Rubin NVL72 trays at GTC Berlin — NVIDIAAI · 2026-10-22
- Court Filing: Meta Told Board It Needs to Raise Hundreds of Billions Starting Fall 2026 — firstadopter · 2026-10-22
- RTX 5090 hotspot hits 98°C in ComfyUI workloads, owner asks for comparisons — HrothgarLover · 2026-10-22