Hugging Face's logo

JEILDLWLRMA
/
Qwen3-VL-4B-Instruct-NVFP4

Image-to-Text
Transformers
Safetensors
qwen3_vl
image-text-to-text
quantized
nvfp4
4bit
vision-language-model
qwen3-vl
compressed-tensors
vllm
smoothquant
8-bit precision
Model card Files
xet
 Community
Qwen3-VL-4B-Instruct-NVFP4

Commit History

Add NVFP4 quantized Qwen3-VL-4B-Instruct (SmoothQuant + NVFP4, 4.1GB)
1443b3f
verified

JEILDLWLRMA commited on

initial commit
87df420
verified

JEILDLWLRMA commited on