YOYO-AI/Qwen3.6-35B-A3B-YOYO-V2
Full fine-tune (fewer layers) vs Qwen/Qwen-AgentWorld-35B-A3B. Qwen/Qwen-AgentWorld-35B-A3B matches part of YOYO-AI/Qwen3.6-35B-A3B-YOYO-V2 (693 of its 1811 tensors; the rest of YOYO-AI/Qwen3.6-35B-A3B-YOYO-V2 has no counterpart). On the shared part: Fine-tune: 100% of the weights changed, across 40 of 40 layers.
Tensors changed: MLP 280/280, Attention 256/280, Norms 131/131, Embeddings 1/1, lm_head 1/1
2 derivatives checked
- mradermacher/Qwen3.6-35B-A3B-YOYO-V2-i1-GGUF: Quantization
- mradermacher/Qwen3.6-35B-A3B-YOYO-V2-GGUF: Quantization