# Can I run Qwen2.5 3B on iPhone 17?

Updated: 2026-06-15

**Yes, it runs.** Runs at Q4_K_M using ~3.3 GB of ~4.5 GB usable.

- Model: 3.09B, Q4_K_M 2.1 GB
- Device: 8 GB unified, ~4.5 GB usable for weights
- Needs ~3.3 GB at Q4_K_M; recommended quant: Q4_K_M
- Best tool on iOS: Apple Foundation Models

Estimate. Method: weights + KV cache + ~0.8GB overhead. Sources: https://ollama.com/library/qwen2.5:3b, https://huggingface.co/Qwen/Qwen2.5-3B-Instruct-GGUF, https://qwenlm.github.io/blog/qwen2.5/.

More: https://localmodel.run/can-i-run/qwen2.5-3b/iphone-17