mradermacher/nsfwvision-qwen3-vl-8b-v3-safetensors-GGUF

Same weights, converted (fewer layers) vs dangerkhan0/nsfwvision-qwen3-vl-8b-v3-safetensors. mradermacher/nsfwvision-qwen3-vl-8b-v3-safetensors-GGUF matches part of dangerkhan0/nsfwvision-qwen3-vl-8b-v3-safetensors (399 of its 750 tensors; the rest of dangerkhan0/nsfwvision-qwen3-vl-8b-v3-safetensors has no counterpart). On the shared part: Same weights stored in another dtype (BF16 → F16/F32).

Tensors changed: Embeddings 0/1, Norms 0/145, MLP 0/108, Attention 0/144, lm_head 0/1

On the Hub · Downloads on Model Pulse