RedHatAI/gemma-4-26B-A4B-it
Full fine-tune vs google/gemma-4-26B-A4B. Fine-tune: 98% of the weights changed, across 30 of 30 layers.
Tensors changed: Embeddings 2/4, MLP 150/231, Norms 211/433, other 59/122, Attention 115/223
2 derivatives checked
- amd/gemma-4-26B-A4B-it-w4a16-llmcompressor: Quantization
- amd/gemma-4-26B-A4B-it-w8a8-llmcompressor: Quantization
53 other repos hold byte-for-byte identical weight files.