Velvet2-3B-Vision

AlmawaveLabs/Velvet2-3B-Vision

Image Text to Text4.3B parameterstransformersLicense: apache-2.0Gated
Tracked by OpenModelStats since October 29, 2026View on Hugging Face ↗
Downloads 30D
63
Total downloads
78
Gained 7D
—
Gained 30D
—
Likes
16
Rank · tracked models
—
–this week
Parameters
4.3B
Last source update
Oct 16, 2026

Downloads over time

Cumulative total downloads observed by OpenModelStats

Likes over time

Rank among tracked models

Lower is better

Not enough tracked history yet for a chart.

OpenModelStats began tracking this model on 2026-10-29. Charts appear as daily observations accumulate.

Overview

Velvet2-3B-Vision is a image text to text model published by AlmawaveLabs. OpenModelStats has tracked the model since Oct 29, 2026, most recently observing it 23h ago.

Published
Oct 14, 2026
Last updated
Oct 16, 2026
Library
transformers
License
apache-2.0
Task
Image Text to Text
Parameters
4,330,374,592
Spaces
—
Derivative models
—
Velocity 7D/day
—
transformerssafetensorsvelvet_vlmfeature-extractionAlmawaveLabsVelvetVision Language ModelVisual Question AnsweringDocument Question Answeringimage-text-to-textconversationalcustom_code

Publisher

AlmawaveLabsView publisher statistics →

Derived from AlmawaveLabs/Velvet2-3B (reported by the source; parent not yet tracked).

Similar models

AlmawaveLabs/Velvet2-3B-Vision — Downloads, Growth & Stats | OpenModelStats