Skip to content
localmodel.run

text model · Sarvam · iOS

S Can I run Sarvam-30B on iPhone 17 Pro?

Compatibility verdict VRAM threshold engine
No, not enough memorywould not load

No. Sarvam-30B needs ~21.7 GB even at Q4_K_M, but iPhone 17 Pro only has ~8 GB usable.

Needs ~21.7 GB Device usable ~8 GB

Needs ~21.7 GB even at Q4_K_M, but only ~8 GB is usable.

Q4_K_M needed
~21.7 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.

Model Sarvam
Parameters
30B (MoE, 2.4B active)
Q4_K_M size
19.6 GB
Context
64k
Full Sarvam-30B requirements →
Device iOS
Memory
12 GB unified
Usable for weights
~8 GB
Best runtime
llama.cpp + Metal (via PocketPal or Off Grid app)
Best models for iPhone 17 Pro →

What you can run instead

Run Sarvam-30B on other hardware

FAQ

Can iPhone 17 Pro run Sarvam-30B?

No. Sarvam-30B needs ~21.7 GB even at Q4_K_M, but iPhone 17 Pro only has ~8 GB usable.

How much memory does Sarvam-30B need?

iPhone 17 Pro does not have enough memory. At Q4_K_M the weights are ~19.6 GB; with KV cache and runtime overhead, budget ~21.7 GB at a 4k context. It is a Mixture-of-Experts model (30B total / 2.4B active), so all experts must stay in memory; memory tracks total params, not active params.

What is the best tool to run Sarvam-30B 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.