YOYO-AI/Qwen3-30B-A3B-Mixture-2507
Full fine-tune vs Qwen/Qwen3-30B-A3B-Instruct-2507. Fine-tune: 100% of the weights changed, across 48 of 48 layers.
Tensors changed: Norms 193/193, MLP 2613/2613, Attention 192/192
4 derivatives checked
- bartowski/YOYO-AI_Qwen3-30B-A3B-Mixture-2507-GGUF: Same weights, converted
- mradermacher/Qwen3-30B-A3B-Mixture-2507-i1-GGUF: Quantization
- mradermacher/Qwen3-30B-A3B-Mixture-2507-GGUF: Quantization
- DevQuasar/YOYO-AI.Qwen3-30B-A3B-Mixture-2507-GGUF: Same weights, converted