bartowski/ConicCat_Qwen3.5-27B-Writer-GGUF

Same weights, converted vs ConicCat/Qwen3.5-27B-Writer. Same weights stored in another dtype (BF16/F32 → BF16/F32), plus 48 new tensors.

Tensors changed: Norms 0/161, lm_head 0/1, Embeddings 0/1, MLP 0/192, Attention 0/64

On the Hub · Downloads on Model Pulse