# Can I run Qwen3 30B-A3B on Generic Android Phone (8GB RAM)?

Updated: 2026-06-15

**No, not enough memory.** Needs ~20.7 GB even at Q4_K_M, but only ~4.5 GB is usable.

- Model: 30.5B (MoE, 3.3B active), Q4_K_M 18.6 GB
- Device: 8 GB ram, ~4.5 GB usable for weights
- Needs ~20.7 GB at Q4_K_M; recommended quant: n/a
- Best tool on Android: PocketPal AI

Estimate. Method: weights + KV cache + ~0.8GB overhead. Sources: https://ollama.com/library/qwen3/tags, https://huggingface.co/unsloth/Qwen3-30B-A3B-GGUF, https://huggingface.co/Qwen/Qwen3-30B-A3B-GGUF, https://qwenlm.github.io/blog/qwen3/, https://lmarena.ai/leaderboard.

More: https://localmodel.run/can-i-run/qwen3-30b-a3b/android-generic-8gb