text model · Sarvam · iOS
S Can I run Sarvam-105B on iPad Pro M4 (16GB, 1TB/2TB config)?
No. Sarvam-105B needs ~67.5 GB even at Q4_K_M, but iPad Pro M4 (16GB, 1TB/2TB config) only has ~12 GB usable.
Needs ~67.5 GB even at Q4_K_M, but only ~12 GB is usable.
- Q4_K_M needed
- ~67.5 GB
- Usable on device
- ~12 GB
- Device memory
- 16 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
- 105B (MoE, 10.3B active)
- Q4_K_M size
- 64.2 GB
- Context
- 128k
- Memory
- 16 GB unified
- Usable for weights
- ~12 GB
- Best runtime
- MLX (via Python or Swift; mlx-lm package)
What you can run instead
Run Sarvam-105B on other hardware
FAQ
Can iPad Pro M4 (16GB, 1TB/2TB config) run Sarvam-105B?
No. Sarvam-105B needs ~67.5 GB even at Q4_K_M, but iPad Pro M4 (16GB, 1TB/2TB config) only has ~12 GB usable.
How much memory does Sarvam-105B need?
iPad Pro M4 (16GB, 1TB/2TB config) does not have enough memory. At Q4_K_M the weights are ~64.2 GB; with KV cache and runtime overhead, budget ~67.5 GB at a 4k context. It is a Mixture-of-Experts model (105B total / 10.3B active), so all experts must stay in memory; memory tracks total params, not active params.
What is the best tool to run Sarvam-105B 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.