yuankongai/Boxer-35B-A3B-v0-0819

Full fine-tune vs Qwen/Qwen3.6-35B-A3B. Fine-tune: 100% of the weights changed, across 40 of 40 layers.

Tensors changed: Embeddings 3/5, Attention 278/392, MLP 343/399, Norms 0/247, lm_head 1/1, other 1/1

2 derivatives checked