# Can I run Sarvam-30B on iPhone 16?

Updated: 2026-06-15

**No, not enough memory.** Needs ~21.7 GB even at Q4_K_M, but only ~4.5 GB is usable.

- Model: 30B (MoE, 2.4B active), Q4_K_M 19.6 GB
- Device: 8 GB unified, ~4.5 GB usable for weights
- Needs ~21.7 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://huggingface.co/sarvamai/sarvam-30b, https://huggingface.co/sarvamai/sarvam-30b-gguf, https://www.sarvam.ai/blogs/sarvam-30b-105b.

More: https://localmodel.run/can-i-run/sarvam-30b/iphone-16