# Can I run DeepSeek-R1-Distill-Qwen 32B on iPhone 17 Pro?

Updated: 2026-06-15

**No, not enough memory.** Needs ~22.1 GB even at Q4_K_M, but only ~8 GB is usable.

- Model: 32B, Q4_K_M 19.85 GB
- Device: 12 GB unified, ~8 GB usable for weights
- Needs ~22.1 GB at Q4_K_M; recommended quant: n/a
- Best tool on iOS: Apple Foundation Models

Estimate. Method: weights + KV cache + ~0.8GB overhead. Sources: https://ollama.com/library/deepseek-r1, https://huggingface.co/bartowski/DeepSeek-R1-Distill-Qwen-32B-GGUF, https://github.com/deepseek-ai/DeepSeek-R1.

More: https://localmodel.run/can-i-run/deepseek-r1-distill-qwen-32b/iphone-17-pro