YOYO-AI/Qwen3-30B-A3B-YOYO-V3
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
3 derivatives checked
- mradermacher/Qwen3-30B-A3B-YOYO-V3-i1-GGUF: Quantization
- mradermacher/Qwen3-30B-A3B-YOYO-V3-GGUF: Quantization
- DavidAU/Qwen3-Yoyo-V3-42B-A3B-Thinking-TOTAL-RECALL-ST-TNG-III: Partial fine-tune