Qwen · 1.5B · Desktop / import

Qwen 2.5 1.5B Instruct on a phone

Previous-gen Qwen that’s still a reliable tiny assistant.

Parameters
1.5B
Typical Q4
~1.0 GB
RAM to budget
~2.2 GB
Engines
GGUF

Get it running

Qwen2.5-1.5B-Instruct; still huge Hugging Face download volume. Hugging Face: Qwen/Qwen2.5-1.5B-Instruct.

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

Tight (close other apps)

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