Qwen · 27B · Desktop / import
Qwen 3.5 27B on a phone
Dense 2026 Qwen for a high-RAM Mac or a 24 GB GPU — then use the phone as the remote keyboard.
- Parameters
- 27B
- Typical Q4
- ~16 GB (Q4)
- RAM to budget
- ~22 GB
- Engines
- GGUF
Get it running
Qwen3.5-27B. Q4 ~16 GB. Also Qwen3.6-27B as a later dense refresh — same RAM class. Hugging Face: Qwen/Qwen3.5-27B.
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.