Runway cuts real-time 57B video model serving from 8 H100s to 4 with inference optimizations

runwayml · x · 2026-11-18

Runway's new research post details how it serves Characters — a 57B-parameter autoregressive video diffusion transformer for real-time conversation — on 4 H100s instead of 8.

The post also covers the production inference system behind keeping natural conversational rhythm past the uncanny valley.

Original post →

More from Infra

Infra channel →