Sa2VA-InternVL3-2B

ByteDance/Sa2VA-InternVL3-2B

Image Text to Text2.3B parameterstransformersLicense: apache-2.0

Tracked by OpenModelStats since October 6, 2026View on Hugging Face ↗

Downloads 30D: 284
Total downloads: 2,680
Gained 7D: —
Gained 30D: —
Likes: 2
Rank · tracked models: —; –this week
Parameters: 2.3B
Last source update: Oct 16, 2025

7D 30D 90D 1Y All

Total downloads Gained per day Rolling recent downloads

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 2026-10-06. Charts appear as daily observations accumulate.

Overview

Sa2VA-InternVL3-2B is a image text to text model published by ByteDance. OpenModelStats has tracked the model since Oct 6, 2026, most recently observing it 11 min ago.

Published: Oct 16, 2025
Last updated: Oct 16, 2025
Library: transformers
License: apache-2.0
Task: Image Text to Text
Parameters: 2,316,157,234
Spaces: —
Derivative models: —
Velocity 7D/day: —

transformerssafetensorssa2va_chatfeature-extractionSa2VAcustom_codeimage-text-to-textconversationalmultilingualarxiv:2501.04001base_model:OpenGVLab/InternVL3-8Bbase_model:merge:OpenGVLab/InternVL3-8B

Publisher

ByteDanceView publisher statistics →

Derived from OpenGVLab/InternVL3-8B (reported by the source; parent not yet tracked).

Similar models

Models similar to Sa2VA-InternVL3-2B
Model	Task	DL 30D	Likes	Params
Qwen3.5-2B-AWQ-4bitcyankiwi	Image Text to Text	5,574	3	2.3B
Qwen3.5-2B-AWQ-INT8-INT4cyankiwi	Image Text to Text	453	2	2.3B
tamil-lm-2b-instructTimegravity	Image Text to Text	453	8	2.3B
gemma-4-E2B-it-qat-mobilemlx-community	Image Text to Text	21.3K	2	2.3B
InternVL3_5-2BOpenGVLab	Image Text to Text	7,183	21	2.3B
InternVL3_5-2B-HFOpenGVLab	Image Text to Text	5,210	3	2.3B