Qwen3-VL-4B-Instruct-3bit

DreamFoundries/Qwen3-VL-4B-Instruct-3bit

Image Text to Text918M parametersmlxLicense: apache-2.0

Tracked by OpenModelStats since August 25, 2026View on Hugging Face ↗

Downloads 30D: 27
Total downloads: 27
Gained 7D: —
Gained 30D: —
Likes: 0
Rank · tracked models: —; –this week
Parameters: 918M
Last source update: Aug 25, 2026

7D 30D 90D 1Y All

Total downloads Gained per day Rolling recent downloads

Downloads over time

Daily gain between consecutive observations

Likes over time

Rank among tracked models

Lower is better

Not enough tracked history yet for a chart.

OpenModelStats began tracking this model on 2026-08-25. Charts appear as daily observations accumulate.

Overview

Qwen3-VL-4B-Instruct-3bit is a image text to text model published by DreamFoundries. OpenModelStats has tracked the model since Aug 25, 2026, most recently observing it 16h ago.

Published: Aug 25, 2026
Last updated: Aug 25, 2026
Library: mlx
License: apache-2.0
Task: Image Text to Text
Parameters: 918,327,808
Spaces: —
Derivative models: —
Velocity 7D/day: —

mlxsafetensorsqwen3_vlvisionimage-text-to-textconversationalbase_model:mlx-community/Qwen3-VL-4B-Instruct-3bitbase_model:quantized:mlx-community/Qwen3-VL-4B-Instruct-3bitlicense:apache-2.03-bitregion:us

Publisher

DreamFoundriesView publisher statistics →

Derived from mlx-community/Qwen3-VL-4B-Instruct-3bit (reported by the source; parent not yet tracked).

Similar models

Models similar to Qwen3-VL-4B-Instruct-3bit
Model	Task	DL 30D	Likes	Params
Qwen3-VL-4B-Instruct-3bitmlx-community	Image Text to Text	267	5	918M
Qwen3-VL-4B-Thinking-3bitmlx-community	Image Text to Text	41	1	918M
DeepSeek-OCR-2-4bitmlx-community	Image Text to Text	230	2	913M
North-Micro-Vision-Instruct-5bit-mlxOpenMed	Image Text to Text	31	1	904M
NVIDIA-Nemotron-Parse-2.0nvidia	Image Text to Text	22.9K	108	903M
NVIDIA-Nemotron-Parse-v1.2nvidia	Image Text to Text	117.3K	69	936M