GLM-OCR reads Nvidia's 61-page 10-Q at 2,086 tok/s for under 2 cents

spillai · x · 2026-09-03

vlmrun ran Nvidia's Q2 10-Q through GLM-OCR via their gateway: 61 pages processed at 2,086 tok/s in 29.54 seconds, costing just $0.019.

The headline number: 2K+ tokens per second and under 2 cents to read a full quarterly filing — a striking datapoint on the speed and price of the latest OCR models for long documents.

Original post →

More from Models

Models channel →