provsalt/Qwen3.8-Flash-Next-NVFP4-PLE-NVFP4
Same weights, repacked vs Inferact/Qwen3.8-Flash-Next-NVFP4. Same weights in different files (re-saved, re-sharded or new metadata), plus 256 new tensors.
Tensors changed: Embeddings 0/9, lm_head 0/1, Norms 0/302, other 0/8, Attention 0/608, MLP 0/1688