Qwen3.8-Flash-Next-W4A16-FP8PLE

albucino/Qwen3.8-Flash-Next-W4A16-FP8PLE

Text Generation72.8B parametersLicense: other
Tracked by OpenModelStats since September 29, 2026View on Hugging Face ↗
Downloads 30D
6,188
Total downloads
6,491
Gained 7D
+3,209(increase)
Gained 30D
—
Likes
51
+9 in 7D
Rank · tracked models
#10,586
343(up 343 places)this week
Parameters
72.8B
Last source update
Oct 2, 2026
Momentum
68.3
  • Qwen3.8-Flash-Next-W4A16-FP8PLE gained 3,209 downloads during the last seven tracked days.
  • It moved from #2825 to #2717 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-W4A16-FP8PLE is a text generation model published by albucino. OpenModelStats has tracked the model since Sep 29, 2026, most recently observing it Oct 6, 2026.

Published
Aug 30, 2026
Last updated
Oct 2, 2026
Library
—
License
other
Task
Text Generation
Parameters
72,758,053,011
Spaces
—
Derivative models
—
Velocity 7D/day
458
safetensorsqwen4_expqwen3.8autoroundint4fp8vllmspeculative-decoding256k-context128k-contextrtx-3090single-gpu

Publisher

albucinoView publisher statistics →

Derived from Intel/Qwen3.8-Flash-Next-W4A16-AutoRound (reported by the source; parent not yet tracked).

Similar models

Models similar to Qwen3.8-Flash-Next-W4A16-FP8PLE
ModelDL 30D
Qwen3.8-Flash-Next-heretic2-W4A16-FP8PLEdensohax3,164
Covenant-72B1Covenant63
Qwen2.5-72B-InstructQwen286.3K
Qwen2-72BQwen24.4K
Qwen2-72B-InstructQwen22.7K
Qwen2.5-72BQwen17.7K