Qwen3-Omni-30B-A3B-Instruct-4bit

mlx-community/Qwen3-Omni-30B-A3B-Instruct-4bit

Any to Any35.3B parameterstransformersLicense: other
Tracked by OpenModelStats since September 30, 2026View on Hugging Face ↗
Downloads 30D
722
Total downloads
2,489
Gained 7D
—
Gained 30D
—
Likes
3
Rank · tracked models
#37,337
223(down 223 places)this week
Parameters
35.3B
Last source update
Dec 24, 2025
  • It moved from #226 to #230 among tracked Any to Any models this week.

Downloads over time

Cumulative total downloads observed by OpenModelStats

Likes over time

Rank among tracked models

Lower is better

Overview

Qwen3-Omni-30B-A3B-Instruct-4bit is a any to any model published by mlx-community. OpenModelStats has tracked the model since Sep 30, 2026, most recently observing it Oct 6, 2026.

Published
Dec 24, 2025
Last updated
Dec 24, 2025
Library
transformers
License
other
Task
Any to Any
Parameters
35,259,818,545
Spaces
—
Derivative models
—
Velocity 7D/day
—
transformerssafetensorsqwen3_omni_moetext-to-audiomultimodalmlxany-to-anyenlicense:otherendpoints_compatible4-bitregion:us

Similar models

Models similar to Qwen3-Omni-30B-A3B-Instruct-4bit
ModelDL 30D
Qwen3-Omni-30B-A3B-InstructQwen655.9K
Qwen3-Omni-30B-A3B-FP8marksverdhei32.4K
Qwen3-Omni-CoderJohnblick1871,199
Qwen3-Omni-30B-A3B-Instruct-5bitmlx-community68
Emu3.5BAAI369
Xiaomi-Robotics-U0XiaomiRobotics59
mlx-community/Qwen3-Omni-30B-A3B-Instruct-4bit — Downloads, Growth & Stats | OpenModelStats