Qwen3.8-Flash-Next-mixed-mlx-K50-min3bit-oMLX

Jakevin/Qwen3.8-Flash-Next-mixed-mlx-K50-min3bit-oMLX

Text Generation91.2B parametersmlxLicense: other
Tracked by OpenModelStats since October 31, 2026View on Hugging Face ↗
Downloads 30D
1,930
Total downloads
1,930
Gained 7D
—
Gained 30D
—
Likes
1
Rank · tracked models
#25,186
522(up 522 places)this week
Parameters
91.2B
Last source update
Nov 1, 2026
  • It moved from #6895 to #6732 among tracked Text Generation models this week.

Downloads over time

Daily gain between consecutive observations

Likes over time

Rank among tracked models

Lower is better

Overview

Qwen3.8-Flash-Next-mixed-mlx-K50-min3bit-oMLX is a text generation model published by Jakevin. OpenModelStats has tracked the model since Oct 31, 2026, most recently observing it Nov 18, 2026.

Published
Oct 30, 2026
Last updated
Nov 1, 2026
Library
mlx
License
other
Task
Text Generation
Parameters
91,214,343,235
Spaces
—
Derivative models
—
Velocity 7D/day
—
mlxsafetensorsqwen4_expomlxmixed-precisionquantizedpruned3-bitmoeapple-silicontext-generationconversational

Publisher

JakevinView publisher statistics →

Derived from Qwen/Qwen3.8-Flash-Next (reported by the source; parent not yet tracked).

Similar models

Models similar to Qwen3.8-Flash-Next-mixed-mlx-K50-min3bit-oMLX
ModelDL 30D
gpt-oss-puzzle-88Bnvidia7,253
DeepSeek-V4.1-Flash-1017-MLX-Serve-Losslessddalcu2,459
Qwen3.8-Flash-Next-VQ-4.4bpwTheDrainFlorist1,785
GLM-5.3-Flash-EXL3-Q40xSero1,159
Qwen3.8-Flash-Next-NVFP4-Abliteratedhuginnfork1,673
Qwen3.8-Flash-Next-NVFP4-Abliteratedlflare1,485
Jakevin/Qwen3.8-Flash-Next-mixed-mlx-K50-min3bit-oMLX — Downloads, Growth & Stats | OpenModelStats