Qwen3-Coder-30B-A3B-Instruct-FP4

NVFP4/Qwen3-Coder-30B-A3B-Instruct-FP4

Text Generation15.6B parametersModel OptimizerLicense: apache-2.0
Tracked by OpenModelStats since September 4, 2026View on Hugging Face ↗
Downloads 30D
11K
Total downloads
160.9K
Gained 7D
+3,238(increase)
2.1%(up) vs baseline
Gained 30D
—
Likes
36
+0 in 7D
Rank · tracked models
#7,621
195(down 195 places)this week
Parameters
15.6B
Last source update
Aug 5, 2025
Momentum
61.5
  • Qwen3-Coder-30B-A3B-Instruct-FP4 gained 3,238 downloads during the last seven tracked days.
  • It moved from #1689 to #1735 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-Coder-30B-A3B-Instruct-FP4 is a text generation model published by NVFP4. OpenModelStats has tracked the model since Sep 4, 2026, most recently observing it Oct 4, 2026.

Published
Aug 5, 2025
Last updated
Aug 5, 2025
Library
Model Optimizer
License
apache-2.0
Task
Text Generation
Parameters
15,583,623,168
Spaces
—
Derivative models
—
Velocity 7D/day
463
Model Optimizersafetensorsqwen3_moenvidiaModelOptQwen3quantizedFP4text-generationconversationalarxiv:2505.09388base_model:Qwen/Qwen3-Coder-30B-A3B-Instruct

Publisher

NVFP4View publisher statistics →

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

Similar models

NVFP4/Qwen3-Coder-30B-A3B-Instruct-FP4 — Downloads, Growth & Stats | OpenModelStats