ManniX-ITA/Qwen3.6-27B-A3B-Coder-MTP-GGUF

Same weights, converted vs ManniX-ITA/Qwen3.6-27B-A3B-Coder. Same weights stored in another dtype (BF16 → F16/F32), plus 170 new tensors.

Tensors changed: Embeddings 0/1, Norms 0/101, MLP 0/200, Attention 0/40, lm_head 0/1

On the Hub · Downloads on Model Pulse