unsloth/Qwen3.5-397B-A17B-GGUF
Same weights, converted vs Qwen/Qwen3.5-397B-A17B. Same weights stored in another dtype (BF16/F32 → BF16/F32), plus 225 new tensors.
Tensors changed: lm_head 0/1, Embeddings 0/1, Attention 0/60, MLP 0/300, Norms 0/151
Same weights, converted vs Qwen/Qwen3.5-397B-A17B. Same weights stored in another dtype (BF16/F32 → BF16/F32), plus 225 new tensors.
Tensors changed: lm_head 0/1, Embeddings 0/1, Attention 0/60, MLP 0/300, Norms 0/151