# Can I run DeepSeek-V2-Lite on Generic Android Phone (8GB RAM)?

Updated: 2026-06-15

**No, not enough memory.** Needs ~12.2 GB even at Q4_K_M, but only ~4.5 GB is usable.

- Model: 16B (MoE, 2.4B active), Q4_K_M 10.4 GB
- Device: 8 GB ram, ~4.5 GB usable for weights
- Needs ~12.2 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/deepseek-v2, https://huggingface.co/deepseek-ai/DeepSeek-V2-Lite, https://huggingface.co/mradermacher/DeepSeek-V2-Lite-GGUF, https://github.com/deepseek-ai/DeepSeek-V2.

More: https://localmodel.run/can-i-run/deepseek-v2-lite/android-generic-8gb