Your phone can't run the new Qwen 3.8 27B model.
Not alone, anyway. I built SwarmLLM. I taught the model to share. It splits a large language model across the devices around you and runs it in browser tabs. In this demo it's Qwen 3.8 27B on my MacBook and my iPhone together.
Long context is where this gets useful.
Qwen 3.8 Flash Next supports: 262K tokens natively. Up to 1 MILLION tokens using YaRN. That means an agent could analyze huge collections of documents, community discussions, customer notes, or coaching calls in one workflow.
I asked Qwen 3.8-Flash-Next to run overnight optimizing a single website about the history of computers.
I gave it a messy prompt and let it figure it out. Prompt in first comment 👇
Qwen 3.8 Max Full COURSE 1 HOUR (Build & Automate Anything)
You have reached the end of the archive
All of qwen38