# Can I run DeepSeek V3 on iPad Pro M4 (16GB, 1TB/2TB config)?

> **No, not enough memory.** Needs ~383.7 GB even at Q4_K_M, but only ~12 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).
- iPad Pro M4 (16GB, 1TB/2TB config): 16 GB unified, ~12 GB usable for model weights.
- Headroom: ~-371.7 GB.

## How to run
Recommended quant: n/a. Best tool on iOS: Apple Foundation Models.

## Other models that run on iPad Pro M4 (16GB, 1TB/2TB config)
- [Phi-4 14B (14B)](https://localmodel.run/can-i-run/phi-4-14b/ipad-pro-m4-16gb)
- [Qwen2.5 14B (14B)](https://localmodel.run/can-i-run/qwen2.5-14b/ipad-pro-m4-16gb)
- [Qwen3 14B (14B)](https://localmodel.run/can-i-run/qwen3-14b/ipad-pro-m4-16gb)
- [DeepSeek-R1-Distill-Qwen 14B (14B)](https://localmodel.run/can-i-run/deepseek-r1-distill-qwen-14b/ipad-pro-m4-16gb)
- [Qwen2.5 Coder 14B (14B)](https://localmodel.run/can-i-run/qwen2.5-coder-14b/ipad-pro-m4-16gb)
- [Mistral Nemo 12B (12.2B)](https://localmodel.run/can-i-run/mistral-nemo-12b/ipad-pro-m4-16gb)

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/ipad-pro-m4-16gb