# Can I run DeepSeek V3 on Generic Android Phone (12GB RAM)?

> **No, not enough memory.** Needs ~383.7 GB even at Q4_K_M, but only ~8.5 GB is usable.

Last validated: 2026-06-15.

## Memory math
- DeepSeek V3: 671B (MoE, 37B active); Q4_K_M weighs 376.66 GB on disk.
- At Q4_K_M with a 4k context it needs ~383.7 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: ~-375.2 GB.

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

## 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://ollama.com/library/deepseek-v3, https://ollama.com/library/deepseek-v3/tags, https://huggingface.co/unsloth/DeepSeek-V3-0324-GGUF, https://huggingface.co/deepseek-ai/DeepSeek-V3-0324.
More: https://localmodel.run/can-i-run/deepseek-v3/android-generic-12gb