Qwen3-VL-4B-Instruct-Uncensored-FP8

NOTE: Do Not quantize this model use the full FP32 Training when quantizing https://huggingface.co/Felldude/Qwen3-VL-4B-Instruct-Uncensored

This model has been finetuned with image and text pairs at 1024px and shows high affinity with limited hallucination on NSFW task.

Full FP32 Training with blockwise conversion to FP8 (Key Blocks in FP32)

This model has limited video caption ability.