text model · Sarvam · iOS
S Can I run Sarvam-M 24B on iPhone Air?
No. Sarvam-M 24B needs ~16.3 GB even at Q4_K_M, but iPhone Air only has ~8 GB usable.
Needs ~16.3 GB even at Q4_K_M, but only ~8 GB is usable.
- Q4_K_M needed
- ~16.3 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
- 24B
- Q4_K_M size
- 14.3 GB
- Q8_0 size
- 25.1 GB
- Context
- 32k
- 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 Sarvam-M 24B on other hardware
FAQ
Can iPhone Air run Sarvam-M 24B?
No. Sarvam-M 24B needs ~16.3 GB even at Q4_K_M, but iPhone Air only has ~8 GB usable.
How much memory does Sarvam-M 24B need?
iPhone Air does not have enough memory. At Q4_K_M the weights are ~14.3 GB; with KV cache and runtime overhead, budget ~16.3 GB at a 4k context.
What is the best tool to run Sarvam-M 24B 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.