noctrex/Qwen3.6-35B-A3B-MXFP4_MOE-GGUF

Same weights, converted vs Qwen/Qwen3.6-35B-A3B. Same weights stored in another dtype (BF16 → MXFP4/F16), plus 150 new tensors.

Tensors changed: Embeddings 0/1, Norms 0/101, MLP 0/160, Attention 0/40, lm_head 0/1

1 derivatives checked

• hugypufy/Qwen3.6-35B-A3B-MXFP4_MOE-GGUF: Quantization

On the Hub · Downloads on Model Pulse