Qwen · 0.8B · Desktop / import

Qwen 3.5 0.8B on a phone

2026 Qwen tiny — hybrid long-context brain in a phone-sized file. Best when you want the newest Qwen on 4–6 GB devices.

Parameters
0.8B
Typical Q4
~500–600 MB
RAM to budget
~1.5 GB
Engines
GGUF · MLX

Get it running

Qwen3.5-0.8B (Feb 2026). Gated DeltaNet hybrid; 262K native context. Community GGUF/MLX as engines catch up — import in LM Mini or host via Connect. Hugging Face: Qwen/Qwen3.5-0.8B.

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.