Qwen · 30B · Desktop / import

Qwen 3 30B-A3B Instruct on a phone

Mixture-of-experts: 30B total, ~3B active. Big-model taste on a strong Mac or GPU.

Parameters
30B
Typical Q4
~16 GB (Q4 MoE)
RAM to budget
~20 GB
Engines
GGUF

Get it running

Qwen3-30B-A3B-Instruct-2507 MoE. Q4 is lighter than dense 30B; still not a phone model. Hugging Face: Qwen/Qwen3-30B-A3B-Instruct-2507.

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

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

Tight (close other apps)

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