TheDrummer/Orion-26B-A4B-v1.1
Full fine-tune vs google/gemma-4-26B-A4B-it. Fine-tune: 95% of the weights changed, across 30 of 30 layers.
Tensors changed: Embeddings 0/4, MLP 150/231, Norms 0/433, other 0/122, Attention 115/223
9 derivatives checked
- bartowski/TheDrummer_Orion-26B-A4B-v1.1-GGUF: Same weights, converted
- mradermacher/Orion-26B-A4B-v1.1-i1-GGUF: Quantization
- mradermacher/Orion-26B-A4B-v1.1-GGUF: Quantization
- Abiray/Orion-26B-A4B-v1.1-GGUF: Quantization
- K4r14/Orion-26B-A4B-v1.1-APEX-GGUF: Quantization
- ailexleon/Orion-26B-A4B-v1.1-mlx-4Bit: Quantization
- ailexleon/Orion-26B-A4B-v1.1-mlx-6Bit: Quantization
- ailexleon/Orion-26B-A4B-v1.1-mlx-8Bit: Quantization
- Czarj/Z_Basorion_0.1: Full fine-tune (fewer layers)