Qwen3-30B-A3B-Thinking-2507-FP8

Qwen/Qwen3-30B-A3B-Thinking-2507-FP8

Text Generation30.5B parameterstransformersLicense: apache-2.0
Tracked by OpenModelStats since August 24, 2026View on Hugging Face ↗
Downloads 30D
21.7K
Total downloads
599.3K
Gained 7D
+5,901(increase)
1.0%(up) vs baseline
Gained 30D
—
Likes
67
+0 in 7D
Rank · tracked models
#5,443
39(down 39 places)this week
Parameters
30.5B
Last source update
Jul 30, 2025
Momentum
60.1
  • Qwen3-30B-A3B-Thinking-2507-FP8 gained 5,901 downloads during the last seven tracked days.
  • It moved from #1234 to #1240 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

Qwen3-30B-A3B-Thinking-2507-FP8 is a text generation model published by Qwen. OpenModelStats has tracked the model since Aug 24, 2026, most recently observing it Oct 4, 2026.

Published
Jul 29, 2025
Last updated
Jul 30, 2025
Library
transformers
License
apache-2.0
Task
Text Generation
Parameters
30,533,947,392
Spaces
—
Derivative models
—
Velocity 7D/day
843
transformerssafetensorsqwen3_moetext-generationconversationalarxiv:2505.09388base_model:Qwen/Qwen3-30B-A3B-Thinking-2507base_model:quantized:Qwen/Qwen3-30B-A3B-Thinking-2507license:apache-2.0endpoints_compatiblefp8region:us

Publisher

QwenView publisher statistics →

Derived from Qwen/Qwen3-30B-A3B-Thinking-2507 (reported by the source; parent not yet tracked).

Similar models

Models similar to Qwen3-30B-A3B-Thinking-2507-FP8
ModelDL 30D
Qwen3-Coder-30B-A3B-Instruct-FP8Qwen1.1M
Qwen3-30B-A3B-Instruct-2507-FP8Qwen392K
Qwen3-30B-A3B-FP8Qwen192.2K
Qwen3-30B-A3B-FP8-blockRedHatAI2,762
Qwen3-30B-A3BQwen1.5M
Qwen3-30B-A3B-Instruct-2507Qwen896.8K