Qwen3.8-Flash-Next-DERISKED-MTPLX-Optimized-Speed

p0ly31/Qwen3.8-Flash-Next-DERISKED-MTPLX-Optimized-Speed

Text Generation126B parametersmlxLicense: other
Tracked by OpenModelStats since September 4, 2026View on Hugging Face ↗
Downloads 30D
1,036
Total downloads
1,175
Gained 7D
+329(increase)
Gained 30D
—
Likes
5
+1 in 7D
Rank · tracked models
#33,029
206(down 206 places)this week
Parameters
126B
Last source update
Sep 4, 2026
Momentum
51.0
  • Qwen3.8-Flash-Next-DERISKED-MTPLX-Optimized-Speed gained 329 downloads during the last seven tracked days.
  • It moved from #8696 to #8757 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-Flash-Next-DERISKED-MTPLX-Optimized-Speed is a text generation model published by p0ly31. OpenModelStats has tracked the model since Sep 4, 2026, most recently observing it Oct 4, 2026.

Published
Sep 4, 2026
Last updated
Sep 4, 2026
Library
mlx
License
other
Task
Text Generation
Parameters
125,743,653,795
Spaces
—
Derivative models
—
Velocity 7D/day
47
mlxsafetensorsqwen4_expapple-siliconmacosspeculative-decodingmulti-token-predictionqwenqwen3.8-flash-nextmoemtpmtplx

Publisher

p0ly31View publisher statistics →

Derived from Blackfrost-AI/Qwen3.8-Flash-Next-DERISKED-BF16 (reported by the source; parent not yet tracked).

Similar models

Models similar to Qwen3.8-Flash-Next-DERISKED-MTPLX-Optimized-Speed
ModelDL 30D
Qwen3.8-Flash-Next-MLX-4bit-MTPKandandan477
GLM-5.3-DQ4-Q5-q8mlx-community486
Qwen3.8-Flash-Next-MTPLX-Bare-SpeedYoussofal3,821
Mistral-Large-Instruct-2407-bnb-4bitunsloth125
Vinci-Cyber-123B-1.0simpledirect1,821
Devstral-2-123B-Instruct-2512-6bitmlx-community138
p0ly31/Qwen3.8-Flash-Next-DERISKED-MTPLX-Optimized-Speed — Downloads, Growth & Stats | OpenModelStats