maeuryhoisj/Qwen3.8-27B-pi-exl3-5bpw
Same weights, converted vs bytkim/Qwen3.8-27B-pi. Same weights stored in another dtype (BF16 → I16/BF16), plus 2373 new tensors.
Tensors changed: Embeddings 0/4, Norms 0/319, Attention 0/267, MLP 0/26
Same weights, converted vs bytkim/Qwen3.8-27B-pi. Same weights stored in another dtype (BF16 → I16/BF16), plus 2373 new tensors.
Tensors changed: Embeddings 0/4, Norms 0/319, Attention 0/267, MLP 0/26