Hugging Face's logo

JEILDLWLRMA
/
Qwen3-VL-8B-Instruct-NVFP4-FP8-Dynamic

Image-to-Text
Transformers
Safetensors
qwen3_vl
image-text-to-text
quantized
nvfp4
fp8
vision-language-model
qwen3-vl
compressed-tensors
vllm
Model card Files
xet
Community
Qwen3-VL-8B-Instruct-NVFP4-FP8-Dynamic / processor_config.json

Commit History

v3.1: Add quantization_config to config.json for proper tensor format detection
5e5a9e3
verified

JEILDLWLRMA commited on