# Can I run Llama 3.3 70B on Generic Android Phone (8GB RAM)?

> **No, not enough memory.** Needs ~45.3 GB even at Q4_K_M, but only ~4.5 GB is usable.

Last validated: 2026-06-15.

## Memory math
- Llama 3.3 70B: 70B; Q4_K_M weighs 42.52 GB on disk.
- At Q4_K_M with a 4k context it needs ~45.3 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: ~-40.8 GB.

## How to run
Recommended quant: n/a. Best tool on Android: PocketPal AI.

## Run Llama 3.3 70B on other devices
- [Apple M4 Max (64GB)](https://localmodel.run/can-i-run/llama-3.3-70b/apple-m4-max-64gb)
- [Apple M4 Max (128GB)](https://localmodel.run/can-i-run/llama-3.3-70b/apple-m4-max-128gb)
- [Apple M5 Max (128GB)](https://localmodel.run/can-i-run/llama-3.3-70b/apple-m5-max-128gb)
- [Apple M3 Ultra (256GB)](https://localmodel.run/can-i-run/llama-3.3-70b/apple-m3-ultra-256gb)

## 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/llama3.3, https://ollama.com/library/llama3.3/tags, https://huggingface.co/bartowski/Llama-3.3-70B-Instruct-GGUF, https://lmarena.ai/leaderboard.
More: https://localmodel.run/can-i-run/llama-3.3-70b/android-generic-8gb