πŸ“‹ Model Description


license: apache-2.0 base_model:
  • thesby/Qwen3-VL-8B-NSFW-Caption-V4
basemodelrelation: quantized tags:
  • qwen3-vl
  • multimodal
  • gguf

-----Important-----

These weights have been updated several times if you downloaded weights from this repo before October 30th they will not work with current llamacpp!!!

The current weights are converted with and tested on mainline llamacpp, derivative projects may or may not work.

πŸ“‚ GGUF File List

πŸ“ Filename πŸ“¦ Size ⚑ Download
qwen3-vl-8B-nsfw-caption-v4-bf16-mmproj.gguf
Recommended LFS FP16
1.08 GB Download
qwen3-vl-8B-nsfw-caption-v4-bf16.gguf
LFS FP16
15.26 GB Download
qwen3-vl-8b-nsfw-caption-q5_K_M.gguf
LFS Q5
5.45 GB Download
qwen3-vl-8b-nsfw-caption-q8_0.gguf
LFS Q8
8.11 GB Download