10T Parameter Models Achieve 1000 TPS Inference

legit_api · x · 2026-08-19

A tweet reveals that 10T parameter models have achieved an inference speed of 1000 TPS. The author questions what AGI labs are waiting for, suggesting that such capabilities imply they should be training significantly more powerful models. This sparks speculation about current technical benchmarks and undisclosed lab progress.

Original post →

More from Infra

Infra channel →