Qwen · 2B · Desktop / import

Qwen 3.5 2B on a phone

Newest small Qwen that still fits everyday phones — sharper than 1.7B-class, still downloadable on cellular.

Parameters
2B
Typical Q4
~1.3–1.5 GB
RAM to budget
~2.7 GB
Engines
GGUF · MLX

Get it running

Qwen3.5-2B. Hybrid attention + native multimodal in the 3.5 family. Prefer Q4 GGUF once your llama.cpp/MLX build lists Qwen3.5. Hugging Face: Qwen/Qwen3.5-2B.

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)