apple/SimpleSD-4B-thinking

Partial fine-tune vs Qwen/Qwen3-4B-Thinking-2507. Partial change: 86% of the weights changed (attention, mlp, norms), in 36 of 36 layers.

Tensors changed: Embeddings 0/1, Norms 76/145, MLP 102/108, Attention 139/144

2 derivatives checked

• mradermacher/SimpleSD-4B-thinking-i1-GGUF: Quantization
• mradermacher/SimpleSD-4B-thinking-GGUF: Same weights, converted

On the Hub · Downloads on Model Pulse