0x795E2795/Obsidian-Alpha-26B-A4B-it-qat-q4_0
Full fine-tune vs google/gemma-4-26B-A4B. 0x795E2795/Obsidian-Alpha-26B-A4B-it-qat-q4_0 is a GGUF (Q4_0/Q8_0) of different weights. Fine-tune: 100% of the weights changed, across 30 of 30 layers.
Tensors changed: Embeddings 1/1, Norms 211/271, MLP 90/90, other 30/30, Attention 115/115