ReadyArt/Dark-Scarlett-v1.0-31B
Full fine-tune vs google/gemma-4-31B-it. Fine-tune: 98% of the weights changed, across 60 of 60 layers.
Tensors changed: Embeddings 2/4, Norms 241/523, other 50/62, MLP 180/261, Attention 230/338
4 derivatives checked
- mradermacher/Dark-Scarlett-v1.0-31B-i1-GGUF: Quantization (fewer layers)
- mradermacher/Dark-Scarlett-v1.0-31B-GGUF: Quantization (fewer layers)
- ReadyArt/Dark-Scarlett-v1.0-31B-GGUF: Quantization (fewer layers)
- ReadyArt/Dark-Scarlett-v1.0-31B-W4A16_PTQ: Quantization