Downloads · 30 days
83
50% of all-time downloads
Qwen3-30B-A3B-MXFP4
amd-quark/Qwen3-30B-A3B-MXFP4
Qwen3-30B-A3B-MXFP4 is a machine learning model from amd-quark. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
All-time downloads
167
Public
Parameters
16.9B
18.5 GB on disk
Likes
2
Public
Repo makeup
Click a slice to open those files.
.safetensors18.5 GB · 100%
Parameter types
How the weights are stored.
U815.4B · 91%
Model card
From the Hugging Face model README
For research/CI purposes.
Generated with:
export exclude_layers="lm_head *.self_attn.* *.mlp.gate.*"
python3 quantize_quark.py --model_dir Qwen/Qwen3-30B-A3B \
--quant_scheme mxfp4 \
--output_dir Qwen3-30B-A3B-MXFP4 \
--exclude_layers $exclude_layers \
--model_export hf_format
- Type
- qwen3_moe
- Created
- Jul 24, 2026
- Updated
- Jul 24, 2026