# Can I run TinyLlama 1.1B on Generic Android Phone (8GB RAM)?

> **Yes, it runs.** Runs at Q4_K_M using ~1.8 GB of ~4.5 GB usable. You have room for FP16 for higher quality.

Last validated: 2026-06-15.

## Memory math
- TinyLlama 1.1B: 1.1B; Q4_K_M weighs 0.669 GB on disk.
- At Q4_K_M with a 4k context it needs ~1.8 GB (weights + KV cache + ~0.8 GB runtime overhead, ±15% with context length).
- Generic Android Phone (8GB RAM): 8 GB ram, ~4.5 GB usable for model weights.
- Headroom: ~2.7 GB; it also fits FP16 for higher quality.

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

## Run TinyLlama 1.1B on other devices
- [Apple M1 (8GB)](https://localmodel.run/can-i-run/tinyllama-1.1b/apple-m1-8gb)
- [8GB RAM Laptop (CPU/iGPU only)](https://localmodel.run/can-i-run/tinyllama-1.1b/laptop-8gb)
- [iPhone 15 Pro](https://localmodel.run/can-i-run/tinyllama-1.1b/iphone-15-pro)
- [iPhone 16](https://localmodel.run/can-i-run/tinyllama-1.1b/iphone-16)
- [iPhone 16 Pro](https://localmodel.run/can-i-run/tinyllama-1.1b/iphone-16-pro)
- [iPhone 17](https://localmodel.run/can-i-run/tinyllama-1.1b/iphone-17)

## Other models that run on Generic Android Phone (8GB RAM)
- [Gemma 3 4B (4B)](https://localmodel.run/can-i-run/gemma-3-4b/android-generic-8gb)
- [Qwen3 4B (4B)](https://localmodel.run/can-i-run/qwen3-4b/android-generic-8gb)
- [Phi-3.5-mini 3.8B (3.82B)](https://localmodel.run/can-i-run/phi-3.5-mini/android-generic-8gb)
- [Phi-4-mini 3.8B (3.8B)](https://localmodel.run/can-i-run/phi-4-mini-3.8b/android-generic-8gb)
- [Qwen2.5-VL 3B (3.75B)](https://localmodel.run/can-i-run/qwen2.5-vl-3b/android-generic-8gb)
- [Qwen2.5 3B (3.09B)](https://localmodel.run/can-i-run/qwen2.5-3b/android-generic-8gb)

Estimate, not a guarantee. Sources: https://ollama.com/library/tinyllama:1.1b, https://huggingface.co/TheBloke/TinyLlama-1.1B-Chat-v1.0-GGUF, https://github.com/jzhang38/TinyLlama.
More: https://localmodel.run/can-i-run/tinyllama-1.1b/android-generic-8gb