Nemotron-3.5-Parse

nvidia/Nemotron-3.5-Parse

Image Text to Text631M parameterstransformersLicense: openmdw-1.1
Tracked by OpenModelStats since November 5, 2026View on Hugging Face ↗
Downloads 30D
22.3K
Total downloads
22.5K
Gained 7D
—
Gained 30D
—
Likes
159
Rank · tracked models
#5,609
132(up 132 places)this week
Parameters
631M
Last source update
Nov 6, 2026
  • It moved from #732 to #714 among tracked Image Text to Text models this week.

Downloads over time

Cumulative total downloads observed by OpenModelStats

Likes over time

Rank among tracked models

Lower is better

Overview

Nemotron-3.5-Parse is a image text to text model published by nvidia. OpenModelStats has tracked the model since Nov 5, 2026, most recently observing it Nov 12, 2026.

Published
Sep 3, 2026
Last updated
Nov 6, 2026
Library
transformers
License
openmdw-1.1
Task
Image Text to Text
Parameters
630,800,504
Spaces
—
Derivative models
—
Velocity 7D/day
—
transformerssafetensorsnemotron_parsetext-generationVLMOCRParseimage-text-to-textconversationalcustom_codelicense:openmdw-1.1eval-results

Similar models

Models similar to Nemotron-3.5-Parse
ModelDL 30D
Qwen3-VL-8B-Instruct-Batch16mobilint671
Qwen3-VL-8B-Instructmobilint421
FastVLM-0.5B-bf16mlx-community2,340
Qwen3.5-0.8B-NVFP4AxionML1,561
Bina-0.1-KoochikReza2kn1,056
surya-ocr-2-persian-handwriting-369kReza2kn762
nvidia/Nemotron-3.5-Parse — Downloads, Growth & Stats | OpenModelStats