bartowski/Rombos-Qwen2.5-Writer-32b-GGUF
Same weights, converted vs SubtleOne/Rombos-Qwen2.5-Writer-32b. Same weights stored in another dtype (BF16 → F16/F32).
Tensors changed: lm_head 0/1, Embeddings 0/1, Norms 0/129, MLP 0/192, Attention 0/448
Same weights, converted vs SubtleOne/Rombos-Qwen2.5-Writer-32b. Same weights stored in another dtype (BF16 → F16/F32).
Tensors changed: lm_head 0/1, Embeddings 0/1, Norms 0/129, MLP 0/192, Attention 0/448