TheDrummer/Cydonia-24B-v3.1
Full fine-tune vs mistralai/Magistral-Small-2506. Fine-tune: 100% of the weights changed, across 40 of 40 layers.
Tensors changed: Embeddings 1/1, Norms 9/81, MLP 120/120, Attention 160/160, lm_head 1/1
4 derivatives checked
- bartowski/TheDrummer_Cydonia-24B-v3.1-GGUF: Same weights, converted
- mradermacher/Cydonia-24B-v3.1-i1-GGUF: Quantization
- mradermacher/Cydonia-24B-v3.1-GGUF: Quantization
- mlx-community/Cydonia-24B-v3.1-4bit: Quantization