MLX-Qwen3.5-9B-DeepSeek-V4-Flash-4bit

Jackrong/MLX-Qwen3.5-9B-DeepSeek-V4-Flash-4bit

Text Generation9B parametersmlxLicense: apache-2.0
Tracked by OpenModelStats since August 24, 2026View on Hugging Face ↗
Downloads 30D
2,231
Total downloads
21.9K
Gained 7D
+713(increase)
3.5%(up) vs baseline
Gained 30D
—
Likes
18
+1 in 7D
Rank · tracked models
#19,828
394(down 394 places)this week
Parameters
9B
Last source update
Apr 30, 2026
Momentum
77.3
  • MLX-Qwen3.5-9B-DeepSeek-V4-Flash-4bit gained 713 downloads during the last seven tracked days.
  • It moved from #5152 to #5245 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

MLX-Qwen3.5-9B-DeepSeek-V4-Flash-4bit is a text generation model published by Jackrong. OpenModelStats has tracked the model since Aug 24, 2026, most recently observing it Oct 7, 2026.

Published
Apr 30, 2026
Last updated
Apr 30, 2026
Library
mlx
License
apache-2.0
Task
Text Generation
Parameters
8,953,803,264
Spaces
—
Derivative models
—
Velocity 7D/day
102
mlxsafetensorsqwen3_5image-text-to-texttext-generation-inferencetransformersunslothreasoningdistillationdeepseekdeepseek-v4sft

Publisher

JackrongView publisher statistics →

Derived from Jackrong/Qwen3.5-9B-DeepSeek-V4-Flash (reported by the source; parent not yet tracked).

Similar models

Models similar to MLX-Qwen3.5-9B-DeepSeek-V4-Flash-4bit
ModelDL 30D
Ornith-1.5-9B-MLX-4bitornith-ai232.7K
NeoHorse-1-9BTokenRhythm14.3K
Qwen3.8-9B-heretic-uncensored-4bit-MTPLXForesee13K
Qwen3.8-9B-mlx-4BitkeXjos5,133
MLX-Qwopus3.5-9B-v3-4bitJackrong4,673
Huihui-Qwen3.5-9B-abliterated-GPTQ-Pro-4bit-g64groxaxo4,061