Downloads · 30 days
15
3% of all-time downloads
Qwen3-30B-A3B-NVFP4-ModelOpt
vroomfondel/Qwen3-30B-A3B-NVFP4-ModelOpt
Qwen3-30B-A3B-NVFP4-ModelOpt is a text generation model from vroomfondel. Use it when you need the model to write or continue text. It is set up for transformers. The card lists the license as apache-2.0.
NVFP4 quantization of Qwen/Qwen3-30B-A3B via NVIDIA ModelOpt.
All-time downloads
546
Public
Parameters
15.6B
18.1 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors18.1 GB · 100%
Parameter types
How the weights are stored.
U814.9B · 86%
Try a prompt
Base models
Model card
From the Hugging Face model README
qwen3-30b-a3b-nvfp4-modelopt
NVFP4 quantization of Qwen/Qwen3-30B-A3B via NVIDIA ModelOpt.
<!-- BEGIN quant:preview -->Quantization details (auto-generated)
- source model: Qwen/Qwen3-30B-A3B
- qformat:
nvfp4kv_cache:fp8 - calibration:
512samples frompg19, cnn_dailymail - producer: NVIDIA ModelOpt
0.45.0 - generated: 2026-07-10T13:08:52Z
Before/after sample generation was skipped for this run (SKIP_GENERATE=1).
- Task
- Text Generation
- Library
- transformers
- Type
- qwen3_moe
- License
- apache-2.0
- Created
- Jul 10, 2026
- Updated
- Jul 15, 2026