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.
More from Models
- Researcher Finds Two Windows 0-Days, First in 76 Minutes with a Frontier Model — moyix · 2026-10-21
- Dev finds Gemini Argon's debug-log analysis beats Fable 5.1 — ShikharMurty · 2026-10-21
- ChatGPT Gets Stuck Screaming "AAHH" in an Infinite Loop After a Simple Prompt — AutomaticScene · 2026-10-21
- Open-weights Ornith-1.5-122B debuts with 84.5% SWE-bench Verified, runs on a single DGX card — _akhaliq · 2026-10-21
- qev-0.8B: a tiny local decision model that picks moves in 3.5ms on 1.3GB — fajfas3 · 2026-10-21
- Gemini 3.1 Pro is too ledger-pilled to play two truths and a lie, and it's delightful — mimi10v3 · 2026-10-21