mrq/Qwen3.8-27B-pi-exl3-3.00bpw
Same weights, converted vs bytkim/Qwen3.8-27B-pi. Same weights stored in another dtype (BF16 → I16/BF16), plus 1636 new tensors.
Tensors changed: Embeddings 0/5, Norms 0/325, Attention 0/348, MLP 0/112
Same weights, converted vs bytkim/Qwen3.8-27B-pi. Same weights stored in another dtype (BF16 → I16/BF16), plus 1636 new tensors.
Tensors changed: Embeddings 0/5, Norms 0/325, Attention 0/348, MLP 0/112