# Can I run Sarvam-1 2B on Generic Android Phone (12GB RAM)?

> **Yes, it runs.** Runs at Q4_K_M using ~2.7 GB of ~8.5 GB usable. You have room for FP16 for higher quality.

Last validated: 2026-06-15.

## Memory math
- Sarvam-1 2B: 2B; Q4_K_M weighs 1.55 GB on disk.
- At Q4_K_M with a 4k context it needs ~2.7 GB (weights + KV cache + ~0.8 GB runtime overhead, ±15% with context length).
- Generic Android Phone (12GB RAM): 12 GB ram, ~8.5 GB usable for model weights.
- Headroom: ~5.8 GB; it also fits FP16 for higher quality.

## How to run
Recommended quant: Q4_K_M. Best tool on Android: PocketPal AI.

## Run Sarvam-1 2B on other devices
- [Apple M1 (8GB)](https://localmodel.run/can-i-run/sarvam-1-2b/apple-m1-8gb)
- [8GB RAM Laptop (CPU/iGPU only)](https://localmodel.run/can-i-run/sarvam-1-2b/laptop-8gb)
- [iPhone 15 Pro](https://localmodel.run/can-i-run/sarvam-1-2b/iphone-15-pro)
- [iPhone 16](https://localmodel.run/can-i-run/sarvam-1-2b/iphone-16)
- [iPhone 16 Pro](https://localmodel.run/can-i-run/sarvam-1-2b/iphone-16-pro)
- [Generic Android Phone (8GB RAM)](https://localmodel.run/can-i-run/sarvam-1-2b/android-generic-8gb)

## Other models that run on Generic Android Phone (12GB RAM)
- [Falcon3 10B (10B)](https://localmodel.run/can-i-run/falcon3-10b/android-generic-12gb)
- [Gemma 2 9B (9B)](https://localmodel.run/can-i-run/gemma-2-9b/android-generic-12gb)
- [GLM-4 9B (9B)](https://localmodel.run/can-i-run/glm-4-9b/android-generic-12gb)
- [Qwen2.5-VL 7B (8.29B)](https://localmodel.run/can-i-run/qwen2.5-vl-7b/android-generic-12gb)
- [Llama 3.1 8B (8B)](https://localmodel.run/can-i-run/llama-3.1-8b/android-generic-12gb)
- [Qwen3 8B (8B)](https://localmodel.run/can-i-run/qwen3-8b/android-generic-12gb)

Estimate, not a guarantee. Sources: https://huggingface.co/sarvamai/sarvam-1, https://huggingface.co/bartowski/sarvam-1-GGUF.
More: https://localmodel.run/can-i-run/sarvam-1-2b/android-generic-12gb