qwen-3-vl-4b-instruct-int2

SJTU-compression/qwen-3-vl-4b-instruct-int2

Image Text to Text4.4B parameterstransformersLicense: apache-2.0

Tracked by OpenModelStats since September 24, 2026View on Hugging Face ↗

Downloads 30D: 8
Total downloads: 8
Gained 7D: —
Gained 30D: —
Likes: 0
Rank · tracked models: —; –this week
Parameters: 4.4B
Last source update: Sep 24, 2026

7D 30D 90D 1Y All

Total downloads Gained per day Rolling recent downloads

Downloads over time

Rolling recent-window downloads as reported

Likes over time

Rank among tracked models

Lower is better

Not enough tracked history yet for a chart.

OpenModelStats began tracking this model on 2026-09-24. Charts appear as daily observations accumulate.

Overview

qwen-3-vl-4b-instruct-int2 is a image text to text model published by SJTU-compression. OpenModelStats has tracked the model since Sep 24, 2026, most recently observing it Sep 25, 2026.

Published: Sep 24, 2026
Last updated: Sep 24, 2026
Library: transformers
License: apache-2.0
Task: Image Text to Text
Parameters: 4,437,815,808
Spaces: —
Derivative models: —
Velocity 7D/day: —

transformerssafetensorsqwen3_vlimage-text-to-textquantizationqatint2multimodaldistillationconversationalbase_model:Qwen/Qwen3-VL-4B-Instructbase_model:finetune:Qwen/Qwen3-VL-4B-Instruct

Publisher

SJTU-compressionView publisher statistics →

Derived from Qwen/Qwen3-VL-4B-Instruct (reported by the source; parent not yet tracked).

Similar models

Models similar to qwen-3-vl-4b-instruct-int2
Model	Task	DL 30D	Likes	Params
Qwen3-VL-4B-InstructQwen	Image Text to Text	3.3M	482	4.4B
Qwen3-VL-4B-Instruct-MLX-4bitlmstudio-community	Image Text to Text	110.3K	12	4.4B
Qwen3-VL-4B-Instruct-MLX-6bitlmstudio-community	Image Text to Text	105.1K	2	4.4B
Qwen3-VL-4B-Instruct-MLX-8bitlmstudio-community	Image Text to Text	104.4K	2	4.4B
Qwen3-VL-4B-Instruct-MLX-5bitlmstudio-community	Image Text to Text	104K	1	4.4B
Qwen3-VL-4B-ThinkingQwen	Image Text to Text	56.1K	120	4.4B