Apple releases SimpleSD-30B-instruct, a self-distilled Qwen code model for research

Apple has released apple/SimpleSD-30B-instruct, a research checkpoint built on Qwen that uses Simple Self-Distillation to improve code generation without rewards, verifiers, or teacher models.

On LiveCodeBench, the model scores 55.3% pass@1 on LCBv6 versus 42.4% for its base, Qwen3-30B-A3B-Instruct-2507. The checkpoints are for reproducibility, not optimized Qwen releases, and are available under the Apple Machine Learning Research Model License.