arunprasath/gemma4-cpu-moe-gguf
Full fine-tune vs google/gemma-4-26B-A4B-it. arunprasath/gemma4-cpu-moe-gguf is a GGUF (Q4_0/Q6_K) of different weights. Fine-tune: 100% of the weights changed, across 30 of 30 layers.
Tensors changed: Embeddings 1/1, Norms 199/271, MLP 90/90, other 30/30, Attention 115/115