darrellbest/Qwen3.5-9B-Heretic-GGUF

Same weights, converted vs darrellbest/Qwen3.5-9B-Heretic. Same weights stored in another dtype (BF16/F32 → BF16/F32), plus 39 new tensors.

Tensors changed: lm_head 0/1, Embeddings 0/1, Norms 0/81, MLP 0/96, Attention 0/32

On the Hub · Downloads on Model Pulse