DavidAU/Qwen3-Yoyo-V3-42B-A3B-Thinking-TOTAL-RECALL-ST-TNG-III

Partial fine-tune vs YOYO-AI/Qwen3-30B-A3B-YOYO-V3. Partial change: 9% of the weights changed (attention, lm_head, mlp, norms), in 1 of 48 layers.

Tensors changed: lm_head 1/1, Embeddings 0/1, Norms 5/193, MLP 36/1763, Attention 4/192

2 derivatives checked

• mradermacher/Qwen3-Yoyo-V3-42B-A3B-Thinking-TOTAL-RECALL-ST-TNG-III-i1-GGUF: Quantization
• mradermacher/Qwen3-Yoyo-V3-42B-A3B-Thinking-TOTAL-RECALL-ST-TNG-III-GGUF: Quantization

On the Hub · Downloads on Model Pulse