Verified record · from the answer index

nemoretriever-parse

modeltested · static-verifiedscore 20/100signed passport ✓published 584d ago · verified 2026-10-20

nemoretriever-parse is a tiny autoregressive Vision Language Model (VLM) designed for document transcription from images. It outputs text in reading order. NVIDIA NIM: runs as an API on your own GPUs.

Declared tools (4)

text-and-tables-extractionaivlm-based-optical-character-recognitionnemo-retriever

model:ngc:nim/nvidia/nemoretriever-parse