huihui-ai/Huihui-Qwen3-VL-30B-A3B-Instruct-abliterated
Partial fine-tune vs Qwen/Qwen3-VL-30B-A3B-Instruct. Partial change: 32% of the weights changed (attention, mlp), in 48 of 48 layers.
Tensors changed: Embeddings 0/4, Norms 0/309, MLP 96/268, Attention 48/300, lm_head 0/1
6 derivatives checked
- noctrex/Huihui-Qwen3-VL-30B-A3B-Instruct-abliterated-GGUF: Quantization
- mradermacher/Huihui-Qwen3-VL-30B-A3B-Instruct-abliterated-GGUF: Quantization
- mradermacher/Huihui-Qwen3-VL-30B-A3B-Instruct-abliterated-i1-GGUF: Quantization
- Tipur/Huihui-Qwen3-VL-30B-A3B-Instruct-abliterated-GGUF: Quantization
- McG-221/Huihui-Qwen3-VL-30B-A3B-Instruct-abliterated-Q8_0-GGUF: Quantization
- MLXBits/huihui-qwen3-vl-30b-abliterated-4bit: Quantization
1 other repos hold byte-for-byte identical weight files.