Qwen3.8-4B-mlx-4Bit

SiddhJagani/Qwen3.8-4B-mlx-4Bit

Text Generation4.2B parameterstransformersLicense: apache-2.0
Tracked by OpenModelStats since September 12, 2026View on Hugging Face ↗
Downloads 30D
510
Total downloads
849
Gained 7D
+150(increase)
Gained 30D
—
Likes
1
+0 in 7D
Rank · tracked models
#42,589
270(down 270 places)this week
Parameters
4.2B
Last source update
Aug 20, 2026
Momentum
23.8
  • Qwen3.8-4B-mlx-4Bit gained 150 downloads during the last seven tracked days.
  • It moved from #12035 to #12141 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

Qwen3.8-4B-mlx-4Bit is a text generation model published by SiddhJagani. OpenModelStats has tracked the model since Sep 12, 2026, most recently observing it Sep 19, 2026.

Published
Aug 19, 2026
Last updated
Aug 20, 2026
Library
transformers
License
apache-2.0
Task
Text Generation
Parameters
4,205,751,296
Spaces
—
Derivative models
—
Velocity 7D/day
21
transformerssafetensorsqwen3_5image-text-to-textempero-aiqwen3.5qwen3.8distillationreasoningfunction-callingsftmlx

Publisher

SiddhJaganiView publisher statistics →

Derived from empero-ai/Qwen3.8-4B-Distill (reported by the source; parent not yet tracked).

Similar models

Models similar to Qwen3.8-4B-mlx-4Bit
ModelDL 30D
NeoHorse-1-4BTokenRhythm25K
JevK5alibiserikbay11K
Qwen3.5-4B-OptiQ-4bitmlx-community10.8K
NeoHorse-1-4B-Max-Heretic-Uncensored-TURBOprithivMLmods4,257
JSBAI-Coder-4Bjsbaicenter3,010
AfriqueQwen3.5-4B-50Langs-Instruct-v1McGill-NLP2,865
SiddhJagani/Qwen3.8-4B-mlx-4Bit — Downloads, Growth & Stats | OpenModelStats