Qwen3.8-27B-huihui-abliterated-INT8-W8A16-DFlash2

lued/Qwen3.8-27B-huihui-abliterated-INT8-W8A16-DFlash2

Image Text to Text27.4B parametersvllmLicense: apache-2.0
Tracked by OpenModelStats since September 8, 2026View on Hugging Face ↗
Downloads 30D
386
Total downloads
1,250
Gained 7D
+93(increase)
Gained 30D
—
Likes
6
+0 in 7D
Rank · tracked models
#46,648
691(down 691 places)this week
Parameters
27.4B
Last source update
Aug 21, 2026
Momentum
20.3
  • Qwen3.8-27B-huihui-abliterated-INT8-W8A16-DFlash2 gained 93 downloads during the last seven tracked days.
  • It moved from #4356 to #4392 among tracked Image Text to Text models this week.

Downloads over time

Cumulative total downloads observed by OpenModelStats

Likes over time

Rank among tracked models

Lower is better

Overview

Qwen3.8-27B-huihui-abliterated-INT8-W8A16-DFlash2 is a image text to text model published by lued. OpenModelStats has tracked the model since Sep 8, 2026, most recently observing it 24h ago.

Published
Aug 21, 2026
Last updated
Aug 21, 2026
Library
vllm
License
apache-2.0
Task
Image Text to Text
Parameters
27,356,728,560
Spaces
0
Derivative models
—
Velocity 7D/day
13
vllmsafetensorsqwen3_5qwen3.8abliterateduncensoredcompressed-tensorsw8a16int8quantizeddflash2speculative-decoding

Model family

Based on base-model relationships reported by the source's metadata.

Similar models

Models similar to Qwen3.8-27B-huihui-abliterated-INT8-W8A16-DFlash2
ModelDL 30D
Qwen3.8-27B-MLX-4bitlmstudio-community4.2M
Qwen3.8-27B-MLX-8bitlmstudio-community4M
Qwen3.8-27B-MLX-6bitlmstudio-community4M
Qwen3.8-27B-MLX-5bitlmstudio-community4M
Qwen3.8-27B-4bitmlx-community429K
Qwen3.6-27B-MLX-4bitlmstudio-community302.1K
lued/Qwen3.8-27B-huihui-abliterated-INT8-W8A16-DFlash2 — Downloads, Growth & Stats | OpenModelStats