Qwen3.6-27B-4bit-MTP-MLX-Serve

ddalcu/Qwen3.6-27B-4bit-MTP-MLX-Serve

Text Generation27.4B parametersmlxLicense: apache-2.0
Tracked by OpenModelStats since September 7, 2026View on Hugging Face ↗
Downloads 30D
375
Total downloads
2,279
Gained 7D
+67(increase)
3.4%(up) vs baseline
Gained 30D
—
Likes
8
+1 in 7D
Rank · tracked models
#46,092
98(up 98 places)this week
Parameters
27.4B
Last source update
Jun 11, 2026
Momentum
57.8
  • Qwen3.6-27B-4bit-MTP-MLX-Serve gained 67 downloads during the last seven tracked days.
  • It moved from #13803 to #13734 among tracked Text Generation models this week.

Downloads over time

Rolling recent-window downloads as reported

Likes over time

Rank among tracked models

Lower is better

Overview

Qwen3.6-27B-4bit-MTP-MLX-Serve is a text generation model published by ddalcu. OpenModelStats has tracked the model since Sep 7, 2026, most recently observing it 32h ago.

Published
Jun 11, 2026
Last updated
Jun 11, 2026
Library
mlx
License
apache-2.0
Task
Text Generation
Parameters
27,356,728,560
Spaces
0
Derivative models
—
Velocity 7D/day
10
mlxsafetensorsqwen3_5apple-siliconqwenqwen3mtpmulti-token-predictionspeculative-decodingmlx-servelocal-aitext-generation

Model family

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

Base model

Similar models

Models similar to Qwen3.6-27B-4bit-MTP-MLX-Serve
ModelDL 30D
Ternary-Bonsai-27B-mlx-2bitprism-ml1.1M
Qwen3.8-27B-MTP-NVFP4sakamakismile416.7K
Qwen3.6-27B-AEON-Ultimate-Uncensored-NVFP4AEON-735.2K
Huihui-Qwen3.8-27B-abliterated-NVFP4sakamakismile30.5K
Qwen3.6-27B-AEON-Ultimate-Uncensored-BF16AEON-78,630
Qwen3.8-27B-OBLITERATED-FP8MrPewpy2,610
ddalcu/Qwen3.6-27B-4bit-MTP-MLX-Serve — Downloads, Growth & Stats | OpenModelStats