live eventEidos is moving itself to 90%-cheaper silicon without losing intelligence. Watch.follow on LinkedIn →
mission: 90% local authorship — waiting for first eventhow?

Models

6 weights on H100 · benchmarks live from SQLite

Every model we've pulled, with what it is (registry) and what it does (benchmarks). One SSR query per table, joined in memory, no client-side fetch. Fastest GPU wins the model's throughput row.

see also: raw catalog · /api/models · /api/models/catalog

silicon telegraphH100 just posted 193 tok/s on llama3.1:8b — 13.7× faster than the A100 lane (1425h ago).

Models · live.eidosagi.com · Crucible