DevQuasar/AXCXEPT.Qwen3-EZO-8B-beta-GGUF
Same weights, converted vs AXCXEPT/Qwen3-EZO-8B-beta. Same weights stored in another dtype (BF16 → F16/F32).
Tensors changed: Embeddings 0/1, Norms 0/145, MLP 0/108, Attention 0/144, lm_head 0/1
Same weights, converted vs AXCXEPT/Qwen3-EZO-8B-beta. Same weights stored in another dtype (BF16 → F16/F32).
Tensors changed: Embeddings 0/1, Norms 0/145, MLP 0/108, Attention 0/144, lm_head 0/1