DeepSeek · 1.5B · In LM Mini

DeepSeek R1 Distill 1.5B on a phone

A mini “thinking” model — stronger at math and step-by-step reasoning.

Parameters
1.5B
Typical Q4
~1.0–1.1 GB
RAM to budget
~2.3 GB
Engines
GGUF · MLX

Get it running

R1 distill of Qwen 2.5 1.5B; reasoning traces. GGUF + MLX. Hugging Face: deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B.

In the LM Mini on-device catalog.

Get LM Mini and load a model that actually fits — on-device, or via Connect to a PC.

Phones that can run it

Tight (close other apps)

  • None in this guide — use a Mac or Connect.