Promote Sign in Sign up

Multimodal model

Qwen3-VL-8B-Instruct-NVFP4

Listed for image to text. Explore the model card for usage and requirements.

JEILDLWLRMA Multimodal Open weights apache-2.0
Open model card ↗
Type
Multimodal
Weights
Open
Downloads
96k
Likes
4
Pipeline
image to text
License
apache-2.0

Model hub

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

Repo
JEILDLWLRMA/Qwen3-VL-8B-Instruct-NVFP4
Access
Public
Technical tags and languages
safetensors qwen3_vl vision-language multimodal qwen3-vl nvfp4 quantization llmcompressor smoothquant image-to-text base_model:Qwen/Qwen3-VL-8B-Instruct base_model:quantized:Qwen/Qwen3-VL-8B-Instruct
Open on Hugging Face