mradermacher/Huihui-Qwen3-VL-4B-Instruct-abliterated-GGUF

Same weights, converted (fewer layers) vs huihui-ai/Huihui-Qwen3-VL-4B-Instruct-abliterated. mradermacher/Huihui-Qwen3-VL-4B-Instruct-abliterated-GGUF matches part of huihui-ai/Huihui-Qwen3-VL-4B-Instruct-abliterated (398 of its 713 tensors; the rest of huihui-ai/Huihui-Qwen3-VL-4B-Instruct-abliterated 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

On the Hub · Downloads on Model Pulse