Qwen3.8-27B-mixed-NVFP4-FP8

primitive-ai/Qwen3.8-27B-mixed-NVFP4-FP8

Text Generation17.5B parameterstransformersLicense: apache-2.0
Tracked by OpenModelStats since August 24, 2026View on Hugging Face ↗
Downloads 30D
515
Total downloads
2,114
Gained 7D
+143(increase)
8.2%(up) vs baseline
Gained 30D
—
Likes
6
+0 in 7D
Rank · tracked models
#39,245
587(down 587 places)this week
Parameters
17.5B
Last source update
Aug 27, 2026
Momentum
45.7
  • Qwen3.8-27B-mixed-NVFP4-FP8 gained 143 downloads during the last seven tracked days.
  • It moved from #10675 to #10863 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

Qwen3.8-27B-mixed-NVFP4-FP8 is a text generation model published by primitive-ai. OpenModelStats has tracked the model since Aug 24, 2026, most recently observing it 15h ago.

Published
Aug 17, 2026
Last updated
Aug 27, 2026
Library
transformers
License
apache-2.0
Task
Text Generation
Parameters
17,463,440,112
Spaces
0
Derivative models
—
Velocity 7D/day
20
transformerssafetensorsqwen3_5image-text-to-textvllmcompressed-tensorsnvfp4fp8mixed-precisionquantizedspeculative-decodingblackwell

Model family

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

Similar models

Models similar to Qwen3.8-27B-mixed-NVFP4-FP8
ModelDL 30D
Qwen3-30B-A3B-NVFP4RedHatAI3,158
Qwen3-Coder-30B-A3B-Instruct-NVFP4ig11,308
cogvlm-chat-hfzai-org984
Marco-Mini-InstructATH-MaaS203
Qwen3-32B-NVFP4nvidia13.1K
Param2-17B-A2.4B-Thinkingbharatgenai5,002
primitive-ai/Qwen3.8-27B-mixed-NVFP4-FP8 — Downloads, Growth & Stats | OpenModelStats