barozp/Qwen3.6-29B-REAP-Opus-Reasoning-Distill-MTP-GGUF

Same weights, converted vs barozp/Qwen3.6-29B-REAP-Opus-Reasoning-Distill-MTP. Same weights stored in another dtype (BF16 → BF16/F32), plus 170 new tensors.

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

On the Hub · Downloads on Model Pulse