burtenshaw/GemmaCoder3-12B
Full fine-tune vs google/gemma-3-12b-it. Fine-tune: 97% of the weights changed, across 48 of 48 layers.
Tensors changed: Embeddings 1/4, Norms 207/400, MLP 144/252, Attention 192/408, other 0/1
3 derivatives checked
- bartowski/burtenshaw_GemmaCoder3-12B-GGUF: Same weights, converted (fewer layers)
- mradermacher/GemmaCoder3-12B-i1-GGUF: Quantization (fewer layers)
- mradermacher/GemmaCoder3-12B-GGUF: Quantization (fewer layers)