text model · gemma · iOS
Can I run Gemma 3 12B on iPhone 17 Pro?
No. Gemma 3 12B needs ~8.9 GB even at Q4_K_M, but iPhone 17 Pro only has ~8 GB usable.
Needs ~8.9 GB even at Q4_K_M, but only ~8 GB is usable.
- Q4_K_M needed
- ~8.9 GB
- Usable on device
- ~8 GB
- Device memory
- 12 GB
How to run it
On iOS use Apple Foundation Models (Built into iOS 26, ~3B on-device model, zero download, fully private.). Phones realistically run 1B-4B class models. Anything larger thermally throttles or OOMs.
- Parameters
- 12B
- Q4_K_M size
- 7.3 GB
- Q8_0 size
- 12.51 GB
- Context
- 128k
- Ollama tag
- gemma3:12b
- Memory
- 12 GB unified
- Usable for weights
- ~8 GB
- Best runtime
- llama.cpp + Metal (via PocketPal or Off Grid app)
What you can run instead
Run Gemma 3 12B on other hardware
FAQ
Can iPhone 17 Pro run Gemma 3 12B?
No. Gemma 3 12B needs ~8.9 GB even at Q4_K_M, but iPhone 17 Pro only has ~8 GB usable.
How much memory does Gemma 3 12B need?
iPhone 17 Pro does not have enough memory. At Q4_K_M the weights are ~7.3 GB; with KV cache and runtime overhead, budget ~8.9 GB at a 4k context.
What is the best tool to run Gemma 3 12B on iOS?
On iPhone and iPad, Apple Foundation Models (Built into iOS 26, ~3B on-device model, zero download, fully private.) is the standard choice. Phones realistically run 1B-4B class models. Anything larger thermally throttles or OOMs.
Sources
Memory figures are estimates. See methodology.