Ateron/Gemma-4-MoonGem-31B
Full fine-tune vs AuriAetherwiing/G4-31B-Musica-v1. Fine-tune: 98% of the weights changed, across 60 of 60 layers.
Tensors changed: Embeddings 1/4, Norms 192/523, other 0/62, MLP 180/261, Attention 230/338
5 derivatives checked
- bartowski/Ateron_Gemma-4-MoonGem-31B-GGUF: Same weights, converted (fewer layers)
- mradermacher/Gemma-4-MoonGem-31B-i1-GGUF: Quantization (fewer layers)
- mradermacher/Gemma-4-MoonGem-31B-GGUF: Quantization (fewer layers)
- ailexleon/Gemma-4-MoonGem-31B-mlx-4Bit: Quantization
- ailexleon/Gemma-4-MoonGem-31B-mlx-8Bit: Quantization