QuixiAI/Qwen3-72B-Embiggened-gguf
Same weights, converted vs QuixiAI/Qwen3-72B-Embiggened. Same weights stored in another dtype (BF16 → F16/F32).
Tensors changed: lm_head 0/1, Embeddings 0/1, Norms 0/321, MLP 0/240, Attention 0/320
Same weights, converted vs QuixiAI/Qwen3-72B-Embiggened. Same weights stored in another dtype (BF16 → F16/F32).
Tensors changed: lm_head 0/1, Embeddings 0/1, Norms 0/321, MLP 0/240, Attention 0/320