text model · Sarvam · Android
Can I run Sarvam-105B on Google Pixel 10 Pro?
No. Sarvam-105B needs ~67.5 GB even at Q4_K_M, but Google Pixel 10 Pro only has ~10.5 GB usable.
Needs ~67.5 GB even at Q4_K_M, but only ~10.5 GB is usable.
That figure is at a 4k context and moves about ±15% as context length changes.
The gap is about 57 GB: Sarvam-105B needs roughly 67.5 GB at Q4_K_M and Google Pixel 10 Pro leaves only about 10.5 GB usable for a model. The lightest tracked hardware that runs Sarvam-105B is the Apple M4 Max (128GB) at 128 GB. See Sarvam-105B on Apple M4 Max (128GB).
- Q4_K_M needed
- ~67.5 GB
- Usable on device
- ~10.5 GB
- Device memory
- 16 GB
Which quant fits
How to run it
On Android use PocketPal AI (Polished app, download GGUF and run offline.).
- Parameters
- 105B (MoE, 10.3B active)
- Q4_K_M size
- 64.2 GB
- Context
- 128k
- Memory
- 16 GB ram
- Usable for weights
- ~10.5 GB
- Power draw
- ~7 W
- Best runtime
- llama.cpp (PocketPal) or MLC-LLM (Adreno GPU path)
What you can run instead
Run Sarvam-105B on other hardware
FAQ
Can Google Pixel 10 Pro run Sarvam-105B?
No. Sarvam-105B needs ~67.5 GB even at Q4_K_M, but Google Pixel 10 Pro only has ~10.5 GB usable.
How much memory does Sarvam-105B need?
Google Pixel 10 Pro 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 Android?
On Android, PocketPal AI (Polished app, download GGUF and run offline.) is the go-to option. NPU acceleration is limited and chip-specific; most apps run on CPU. Expect 1B-4B class.
Embed this
A live badge for your model card or README, updated as the data is. [](https://localmodel.run/can-i-run/sarvam-105b/pixel-10-pro) Sources
- 9to5google.com
- gadgetversus.com
- github.com/a-ghorbani
- github.com/google-ai-edge
- github.com/mlc-ai
- github.com/shubham0204
- github.com/Vali-98
- gsmarena.com
- huggingface.co/sarvamai/sarvam-105b
- huggingface.co/sarvamai/sarvam-105b-gguf
- layla-network.ai
- sarvam.ai
- store.google.com/product/pixel_10_pro
- store.google.com/product/pixel_10_pro_specs
Weights are measured from GGUF files; KV cache and overhead are computed, so totals can vary ~15% with context and runtime. Any tok/s is a bandwidth estimate. See methodology.