NVIDIA · DOWNLOADABLE

Nemotron-3.5-Parse

VisionDocument reading

Understands text and images and responds in text.

Listed Sep 3, 2026 · Checked Oct 18, 2026

What it does

Published capability labels: Vision, Document reading. Listed uses: Chat & writing, Image understanding.

Inputs
text, image
Outputs
text
Category
Language
Context window
Not reported
License
openmdw-1.1

These labels describe intended capabilities. Scout has not independently evaluated this model or established that it is best at a particular task.

Model size & local memory

Total parametersNot reportedNot disclosed
4-bit weight storageNot reportedTheoretical weights only

Running requires extra memory for cache, activations, and the runtime. This is not a tested minimum VRAM requirement. A compatible 4-bit download is not guaranteed; mixture-of-experts estimates use total parameters.

No independently verified hardware speed is attached to this profile. You can record your own measurements in the explorer’s My hardware view. Understand the memory estimate.

Cloud pricing

No cloud price is linked to this listing. Cloud API entries are listed separately in the library.

Tested performance

No independent leaderboard result is linked to this model yet. Missing evidence is not a low score. See tested models.

Benchmark evidence

No vendor-reported results have been imported for this model. Missing evidence is not a low score.