GestaltLabs/Qwen3.8-27B-EXL3-11.5GB

Full fine-tune vs Qwen/Qwen3.8-27B. Fine-tune: 91% of the weights changed, across 0 of 64 layers.

Tensors changed: Norms 0/313, Attention 0/319, MLP 0/26, Embeddings 1/1

1 derivatives checked