Qwen · 3B · Desktop / import
Qwen 2.5 3B Instruct on a phone
Compact Qwen for chat and light coding when 4B feels heavy.
- Parameters
- 3B
- Typical Q4
- ~1.9 GB
- RAM to budget
- ~3.2 GB
- Engines
- GGUF
Get it running
Qwen2.5-3B-Instruct Q4_K_M; LM Studio / Ollama. Hugging Face: Qwen/Qwen2.5-3B-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
- iPhone 17 Pro Max Runs well
- iPhone 17 Pro Runs well
- iPhone Air Runs well
- iPhone 17 Fits
- Pixel 10 Pro XL Runs well
- Pixel 10 Pro Runs well
- Pixel 10 Runs well
- Galaxy S26 Ultra Runs well
- iPhone 16 Pro Max Fits
- iPhone 16 Pro Fits
- iPhone 16 Plus Fits
- iPhone 16 Fits
- iPhone 16e Fits
- iPhone 15 Pro Max Fits
- iPhone 15 Pro Fits
- Pixel 9 Pro XL Runs well
- Pixel 9 Pro Runs well
- Pixel 9 Runs well
Tight (close other apps)
- None in this guide — use a Mac or Connect.