Qwen3.6-35B-A3B-MTP-4bit

mlx-community/Qwen3.6-35B-A3B-MTP-4bit

Text Generation845M parametersmlxLicense: apache-2.0
Tracked by OpenModelStats since October 1, 2026View on Hugging Face ↗
Downloads 30D
1,512
Total downloads
8,237
Gained 7D
+424(increase)
6.0%(up) vs baseline
Gained 30D
—
Likes
5
+1 in 7D
Rank · tracked models
#28,454
73(up 73 places)this week
Parameters
845M
Last source update
Jun 1, 2026
Momentum
74.6
  • Qwen3.6-35B-A3B-MTP-4bit gained 424 downloads during the last seven tracked days.
  • It moved from #7394 to #7373 among tracked Text Generation models this week.

Downloads over time

Cumulative total downloads observed by OpenModelStats

Likes over time

Rank among tracked models

Lower is better

Overview

Qwen3.6-35B-A3B-MTP-4bit is a text generation model published by mlx-community. OpenModelStats has tracked the model since Oct 1, 2026, most recently observing it 21h ago.

Published
Jun 1, 2026
Last updated
Jun 1, 2026
Library
mlx
License
apache-2.0
Task
Text Generation
Parameters
844,640,768
Spaces
0
Derivative models
—
Velocity 7D/day
61
mlxsafetensorsqwen3_5_mtpmlx-vlmqwen3.6qwen3.6-35b-a3bqwenmoemtpspeculative-decodingdraft-model4-bit

Model family

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

Similar models

Models similar to Qwen3.6-35B-A3B-MTP-4bit
ModelDL 30D
Qwen3.6-35B-A3B-MTP-5bitmlx-community663
Nanbeige4.2-3B-DSparkNanbeige635
GLM-5.2-0.8B-A0.8Binference-optimization5,152
bitnet-b1.58-2B-4Tmicrosoft20.1K
dgpl-linux-assistant-0.8bdgpl4,260
Qwen3.5-0.8B-hereticsaidutta693,336