Sa2VA-Qwen2_5-VL-7B

ByteDance/Sa2VA-Qwen2_5-VL-7B

Image Text to Text8.5B parameterstransformersLicense: apache-2.0

Tracked by OpenModelStats since September 29, 2026View on Hugging Face ↗

Downloads 30D: 437
Total downloads: 1,859
Gained 7D: —
Gained 30D: —
Likes: 5
Rank · tracked models: #44,003; 110(down 110 places)this week
Parameters: 8.5B
Last source update: Oct 16, 2025

It moved from #4174 to #4192 among tracked Image Text to Text models this week.

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

Overview

Sa2VA-Qwen2_5-VL-7B is a image text to text model published by ByteDance. OpenModelStats has tracked the model since Sep 29, 2026, most recently observing it Oct 6, 2026.

Published: Oct 16, 2025
Last updated: Oct 16, 2025
Library: transformers
License: apache-2.0
Task: Image Text to Text
Parameters: 8,527,538,994
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-Qwen2_5-VL-7B
Model	Task	DL 30D	Likes	Params
LLaVA-OneVision-1.5-8B-Instructlmms-lab	Image Text to Text	17K	67	8.5B
LLaVA-OneVision-2-8B-Instructlmms-lab-encoder	Image Text to Text	8,748	15	8.5B
InternVL3_5-8BOpenGVLab	Image Text to Text	41.1K	108	8.5B
InternVL3_5-8B-HFOpenGVLab	Image Text to Text	33.5K	9	8.5B
InternVL3_5-8B-InstructOpenGVLab	Image Text to Text	2,701	16	8.5B
InternVL3_5-8B-PretrainedOpenGVLab	Image Text to Text	542	2	8.5B