xCloudinfo/xGemable-12B-coder-v2-fullft-GGUF
Full fine-tune vs google/gemma-4-12B-it. xCloudinfo/xGemable-12B-coder-v2-fullft-GGUF is a GGUF (Q8_0) of different weights. Fine-tune: 100% of the weights changed, across 48 of 48 layers.
Tensors changed: Embeddings 1/1, Norms 132/289, MLP 144/144, Attention 184/184