TheUmbraWalker/gemma-4-E4B-it-2-heretic

Full fine-tune vs google/gemma-4-E4B. Fine-tune: 94% of the weights changed, across 42 of 42 layers.

Tensors changed: MLP 126/606, Norms 212/484, other 124/261, Attention 132/719, Embeddings 4/6

2 derivatives checked

• mradermacher/gemma-4-E4B-it-2-heretic-i1-GGUF: Quantization (fewer layers)
• mradermacher/gemma-4-E4B-it-2-heretic-GGUF: Same weights, converted (fewer layers)

On the Hub · Downloads on Model Pulse