noctrex/Qwen3.5-35B-A3B-Claude-4.6-Opus-Reasoning-Distilled-MXFP4_MOE-GGUF

Same weights, converted vs Jackrong/Qwen3.5-35B-A3B-Claude-4.6-Opus-Reasoning-Distilled. Same weights stored in another dtype (BF16/F32 → MXFP4/F16), plus 150 new tensors.

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

On the Hub · Downloads on Model Pulse