Qwen3.6-35B-A3B-PrismaQuant-4.75bit-vllm

rdtand/Qwen3.6-35B-A3B-PrismaQuant-4.75bit-vllm

Image Text to Text21.1B parametersvllmLicense: apache-2.0
Tracked by OpenModelStats since August 29, 2026View on Hugging Face ↗
Downloads 30D
5,622
Total downloads
327K
Gained 7D
+233(increase)
0.1%(up) vs baseline
Gained 30D
—
Likes
35
+0 in 7D
Rank · tracked models
#10,648
95(down 95 places)this week
Parameters
21.1B
Last source update
Apr 21, 2026
Momentum
35.2
  • Qwen3.6-35B-A3B-PrismaQuant-4.75bit-vllm gained 233 downloads during the last seven tracked days.

Downloads over time

Daily gain between consecutive observations

Likes over time

Rank among tracked models

Lower is better

Overview

Qwen3.6-35B-A3B-PrismaQuant-4.75bit-vllm is a image text to text model published by rdtand. OpenModelStats has tracked the model since Aug 29, 2026, most recently observing it Sep 28, 2026.

Published
Apr 20, 2026
Last updated
Apr 21, 2026
Library
vllm
License
apache-2.0
Task
Image Text to Text
Parameters
21,124,964,170
Spaces
—
Derivative models
—
Velocity 7D/day
33
vllmsafetensorsqwen3_5_moeqwen3.6moevision-languagemultimodaldeltanetquantizedmixed-precisionnvfp4mxfp8

Publisher

rdtandView publisher statistics →

Derived from Qwen/Qwen3.6-35B-A3B (reported by the source; parent not yet tracked).

Similar models

rdtand/Qwen3.6-35B-A3B-PrismaQuant-4.75bit-vllm — Downloads, Growth & Stats | OpenModelStats