Alittlehammmer/Qwen3.6-35B-A3B-DFlash-GGUF-llama.cpp

Same weights, converted vs z-lab/Qwen3.6-35B-A3B-DFlash. Same weights stored in another dtype (BF16 → BF16/F32), plus 1 new tensors.

Tensors changed: other 0/1, Norms 0/25, MLP 0/18, Attention 0/24

On the Hub · Downloads on Model Pulse