Qwen3-VL-8B-Instruct-NVFP4 / quantization_config.json
bnjmnmarie's picture
Upload folder using huggingface_hub
112f532 verified
{
"bits": 4,
"group_size": 16,
"sym": true,
"data_type": "nv_fp",
"act_bits": 4,
"act_group_size": 16,
"act_sym": true,
"act_dynamic": true,
"act_data_type": "nv_fp4_with_static_gs",
"autoround_version": "0.8.0",
"block_name_to_quantize": "model.language_model.layers",
"quant_method": "auto-round",
"packing_format": "auto_round:llm_compressor"
}