Submit a benchmark or hardware

Submit a local-LLM speed you measured, a GitHub or Hugging Face repo that states speeds, or hardware the catalogue is missing. Every entry is human-reviewed before it appears.

Snapshot 2026-10-16 · 394 configs on AI boxes and 423 on GPU cards · 123 models. Every number is generated from the tracker snapshot and linked to where it was measured; nothing here is typed by hand.

More: all configs · hardware · news · contributors · methodology · llms.txt · llms-full.txt · API (OpenAPI) · JSON snapshot. Built by Altronis, private on-prem AI, Singapore.