barozp/Qwen3.6-29B-REAP-Opus-Reasoning-Distill-MTP
Same weights, repacked vs barozp/Qwen3.6-29B-REAP-Opus-Reasoning-Distill. Same weights in different files (re-saved, re-sharded or new metadata), plus 19 new tensors.
Tensors changed: lm_head 0/1, Embeddings 0/1, Norms 0/131, Attention 0/280, MLP 0/280
4 derivatives checked
- barozp/Qwen3.6-29B-REAP-Opus-Reasoning-Distill-MTP-GGUF: Same weights, converted
- barozp/Qwen3.6-29B-REAP-Opus-Distill-MTPLX-3bit: Quantization
- barozp/Qwen3.6-29B-REAP-Opus-Reasoning-Distill-MLX-3bit: Quantization
- barozp/Qwen3.6-29B-REAP-Opus-Reasoning-Distill-MLX-4bit: Quantization