Apple releases SimpleSD-4B-thinking, a self-distilled Qwen model for code generation

Apple has published SimpleSD-4B-thinking on Hugging Face, a research checkpoint built on Qwen that improves code generation through Simple Self-Distillation without rewards, verifiers, teacher models, or reinforcement learning.

On LiveCodeBench, it lifts Qwen3-4B-Thinking-2507 from 54.5% to 57.8% pass@1 on LCBv6 and from 59.6% to 63.1% pass@1 on LCBv5.

The model is released as a reproducibility checkpoint under the Apple Machine Learning Research Model License, not as an optimized Qwen release.