Downloads · 30 days
16
16% of all-time downloads
internal-testing-qwen3_0.6b-mxfp4-hadamard
amd-quark/internal-testing-qwen3_0.6b-mxfp4-hadamard
internal-testing-qwen3_0.6b-mxfp4-hadamard 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.
Generated with: CUDAVISIBLEDEVICES=0 python quantizequark.py --modeldir /models/QwenQwen3-0.6B --quantscheme mxfp4 --modelexport hfformat --exportweightformat realquantized --outputdir qwen30.6b-mxfp4-hadamard --quant…
All-time downloads
102
Public
Parameters
546M
868 MB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors857 MB · 98%
Parameter types
How the weights are stored.
BF16311M · 57%
Model card
From the Hugging Face model README
Generated with: CUDA_VISIBLE_DEVICES=0 python quantize_quark.py --model_dir /models/Qwen_Qwen3-0.6B --quant_scheme mxfp4 --model_export hf_format --export_weight_format real_quantized --output_dir qwen3_0.6b-mxfp4-hadamard --quant_algo rotation --quant_algo_config_file rotation ${HADAMARD_CONFIG}
- Type
- qwen3
- Created
- Jan 21, 2026
- Updated
- Jan 21, 2026