WhiskyAKM/Qwen3.6-35B-A3B-GGUF

Same weights, converted vs Qwen/Qwen3.6-35B-A3B. Same weights stored in another dtype (BF16 → BF16/F32), plus 170 new tensors.

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

1 derivatives checked

• WhiskyAKM/Qwen3.6-35B-A3B-NVFP4-GGUF: Quantization

On the Hub · Downloads on Model Pulse