DeepSeek · 14B · Desktop / import
DeepSeek R1 Distill 14B on a phone
Heavy reasoning model for research-style answers on GPU or big Macs.
- Parameters
- 14B
- Typical Q4
- ~8–9 GB (Q4)
- RAM to budget
- ~13 GB
- Engines
- GGUF
Get it running
R1 14B distill; long context CoT; prefer desktop. Hugging Face: deepseek-ai/DeepSeek-R1-Distill-Qwen-14B.
Load in LM Studio or Ollama, then chat from the phone.
Get LM Mini and load a model that actually fits — on-device, or via Connect to a PC.
Phones that can run it
- None in this guide — use a Mac or Connect.
Tight (close other apps)
- None in this guide — use a Mac or Connect.