DanyDA/unsloth_Qwen3.5-122B-A10B-GGUF_UD-IQ4_XS-GGUF-SPLIT
Quantization vs Qwen/Qwen3.5-122B-A10B. DanyDA/unsloth_Qwen3.5-122B-A10B-GGUF_UD-IQ4_XS-GGUF-SPLIT is a GGUF quantization (IQ4_XS) of the same weights: 169 tensors match exactly and 194 within quantization error.
Tensors changed: lm_head 0/1, Embeddings 0/1, Attention 0/48, MLP 0/192, Norms 0/121