mradermacher/nsfwvision-v4_qwen3.5-9b-sft-GGUF
Same weights, converted vs GitMylo/nsfwvision-v4_qwen3.5-9b-sft. Same weights stored in another dtype (BF16/F32 → F16/F32), plus 24 new tensors.
Tensors changed: lm_head 0/1, Embeddings 0/1, MLP 0/96, Attention 0/32, Norms 0/81