NSFWVision qwen3 vl 8b V2 (GGUF)

GGUF quants for https://huggingface.co/GitMylo/nsfwvision-qwen3-vl-8b-v2-safetensors. An experimental model with the vision tower trained and the base model and mmproj frozen, to try and improve understanding.

A finetune of the vision tower of Qwen3-VL-8B-Instruct-abliterated-v2.
Only the vision tower was finetuned, although this could still have some impact on the model's quality and prompt following capabilities.

Downloads last month
145
GGUF
Model size
8B params
Architecture
qwen3vl
Hardware compatibility
Log In to add your hardware

4-bit

5-bit

8-bit

16-bit

Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐Ÿ™‹ Ask for provider support

Model tree for GitMylo/nsfwvision-qwen3-vl-8b-v2-gguf

Quantized
(75)
this model