OpenModelStats

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

lmstudio-community/Qwen3-VL-4B-Instruct-MLX-8bit

Image Text to Text4.4B parametersmlxLicense: apache-2.0
Tracked by OpenModelStats since August 24, 2026View on Hugging Face ↗
Downloads 30D
91.1K
Total downloads
2.6M
Gained 7D
+25.5K(increase)
1.0%(up) vs baseline
Gained 30D
—
Likes
2
+0 in 7D
Rank · tracked models
#2,799
55(down 55 places)this week
Parameters
4.4B
Last source update
Oct 28, 2025
Momentum
62.7
  • Qwen3-VL-4B-Instruct-MLX-8bit gained 25.5K downloads during the last seven tracked days.
  • It moved from #367 to #365 among tracked Image Text to Text models this week.
7D30D90D1YAll
Total downloadsGained per dayRolling recent downloads

Downloads over time

Cumulative total downloads observed by OpenModelStats

Likes over time

Rank among tracked models

Lower is better

Overview

Qwen3-VL-4B-Instruct-MLX-8bit is a image text to text model published by lmstudio-community. OpenModelStats has tracked the model since Aug 24, 2026, most recently observing it 7h ago.

Published
Oct 14, 2025
Last updated
Oct 28, 2025
Library
mlx
License
apache-2.0
Task
Image Text to Text
Parameters
4,437,815,808
Spaces
—
Derivative models
—
Velocity 7D/day
3,648
mlxsafetensorsqwen3_vlimage-text-to-textconversationalbase_model:Qwen/Qwen3-VL-4B-Instructbase_model:quantized:Qwen/Qwen3-VL-4B-Instructlicense:apache-2.08-bitregion:us

Publisher

lmstudio-communityView publisher statistics →

Model family

Based on base-model relationships reported by the source's metadata.

Base model

Sibling models

Similar models

Models similar to Qwen3-VL-4B-Instruct-MLX-8bit
ModelDL 30D
Qwen3-VL-4B-InstructQwen3.2M
Qwen3-VL-4B-Instruct-MLX-4bitlmstudio-community96.2K
Qwen3-VL-4B-Instruct-MLX-6bitlmstudio-community92.1K
Qwen3-VL-4B-Instruct-MLX-5bitlmstudio-community90.9K
Qwen3-VL-4B-ThinkingQwen45K
Qwen3-VL-4B-Instructunsloth38K
lmstudio-community/Qwen3-VL-4B-Instruct-MLX-8bit — Downloads, Growth & Stats | OpenModelStats