Qwen3.8-27B-4bit-MTP-MLX

rapid-mlx/Qwen3.8-27B-4bit-MTP-MLX

Text Generation27.4B parametersmlxLicense: apache-2.0
Tracked by OpenModelStats since August 24, 2026View on Hugging Face ↗
Downloads 30D
833
Total downloads
1,294
Gained 7D
+120(increase)
10.2%(up) vs baseline
Gained 30D
—
Likes
2
+1 in 7D
Rank · tracked models
#32,825
733(down 733 places)this week
Parameters
27.4B
Last source update
Aug 17, 2026
Momentum
65.7
  • Qwen3.8-27B-4bit-MTP-MLX gained 120 downloads during the last seven tracked days.
  • It moved from #8662 to #8860 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

Qwen3.8-27B-4bit-MTP-MLX is a text generation model published by rapid-mlx. OpenModelStats has tracked the model since Aug 24, 2026, most recently observing it Sep 21, 2026.

Published
Aug 17, 2026
Last updated
Aug 17, 2026
Library
mlx
License
apache-2.0
Task
Text Generation
Parameters
27,356,728,560
Spaces
0
Derivative models
—
Velocity 7D/day
17
mlxsafetensorsqwen3_5rapid-mlxqwen3.8qwen3.8-27b4-bitmtpspeculative-decodingtext-generationconversationalen

Model family

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

Similar models

Models similar to Qwen3.8-27B-4bit-MTP-MLX
ModelDL 30D
Ternary-Bonsai-27B-mlx-2bitprism-ml1.1M
Qwen3.8-27B-MTP-NVFP4sakamakismile199.9K
Huihui-Qwen3.8-27B-abliterated-NVFP4sakamakismile66.6K
Qwen3.6-27B-AEON-Ultimate-Uncensored-NVFP4AEON-737.9K
Qwen3.8-27B-AEON-ULTIMATE-UNCENSORED-NVFP4sakamakismile20.3K
Qwen3.8-27B-OBLITERATED-AWQ-W4A16MurtazaNasir13.6K
rapid-mlx/Qwen3.8-27B-4bit-MTP-MLX — Downloads, Growth & Stats | OpenModelStats