Qwen3-VL-4B-Instruct-AWQ-8bit

cyankiwi/Qwen3-VL-4B-Instruct-AWQ-8bit

Image Text to Text2.2B parametersLicense: apache-2.0
Tracked by OpenModelStats since September 5, 2026View on Hugging Face ↗
Downloads 30D
9,972
Total downloads
30.6K
Gained 7D
+981(increase)
3.4%(up) vs baseline
Gained 30D
—
Likes
4
+0 in 7D
Rank · tracked models
#8,174
16(up 16 places)this week
Parameters
2.2B
Last source update
Jul 21, 2026
Momentum
58.6
  • Qwen3-VL-4B-Instruct-AWQ-8bit gained 981 downloads during the last seven tracked days.

Downloads over time

Daily gain between consecutive observations

Likes over time

Rank among tracked models

Lower is better

Overview

Qwen3-VL-4B-Instruct-AWQ-8bit is a image text to text model published by cyankiwi. OpenModelStats has tracked the model since Sep 5, 2026, most recently observing it Oct 5, 2026.

Published
Oct 14, 2025
Last updated
Jul 21, 2026
Library
—
License
apache-2.0
Task
Image Text to Text
Parameters
2,215,326,712
Spaces
—
Derivative models
—
Velocity 7D/day
140
safetensorsqwen3_vlimage-text-to-textconversationalarxiv:2505.09388arxiv:2502.13923arxiv:2409.12191arxiv:2308.12966base_model:Qwen/Qwen3-VL-4B-Instructbase_model:quantized:Qwen/Qwen3-VL-4B-Instructlicense:apache-2.0compressed-tensors

Publisher

cyankiwiView publisher statistics →

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

Similar models

Models similar to Qwen3-VL-4B-Instruct-AWQ-8bit
ModelDL 30D
Eagle2-2Bnvidia1,504
Qwen3.5-2B-FP8surogate943
Infinity-Parser2-Flashinfly21.2K
Qwen3.5-2B-6bitmlx-community9,650
Qwen3.5-2B-4bitmlx-community7,433
Qwen3.5-2B-MLX-4bitlmstudio-community4,605
cyankiwi/Qwen3-VL-4B-Instruct-AWQ-8bit — Downloads, Growth & Stats | OpenModelStats