Nimbz/Gemma-4-Gembrain-X-31B

Full fine-tune vs AuriAetherwiing/G4-31B-Musica-v1. Fine-tune: 94% of the weights changed, across 60 of 60 layers.

Tensors changed: Embeddings 0/4, Norms 143/523, other 0/62, MLP 180/261, Attention 230/338

3 derivatives checked

• Nimbz/Gemma-4-Gembrain-X-31B-GGUF: Quantization (fewer layers)
• mradermacher/Gemma-4-Gembrain-X-31B-i1-GGUF: Quantization (fewer layers)
• mradermacher/Gemma-4-Gembrain-X-31B-GGUF: Quantization (fewer layers)

On the Hub · Downloads on Model Pulse