Loading benchmark data…
EyesInAI·Loading live benchmark data
We have no valid benchmark results for this model yet, so there is no pass rate to report. Pricing and specification above come from the provider catalog.
Measured results only — no recommendation.
Full precision, max quality. KV cache is only ~10GB even at 1M tokens (sparse attention + Engram memory). Self-host economics close ~3–4B tokens/day — below that the API is cheaper.
No benchmark results recorded for this model yet.