Qwen 3.6

Runs on your device

Alibaba's Qwen team · Apr 2026

Top-tier coding, math, and reasoning. The 35B MoE runs fast for its size — only 3B parameters active per token.

Context
256K tokens
Smallest download
12.3 GB
Runs from
24 GB RAM
License
Apache 2.0
codingagenticmathreasoningmultilingualchatMLX for Apple Silicon

Will Qwen 3.6 run on your machine?

This is the same sizing the app uses - not a marketing estimate.

27B16.8 GB downloadToo big for this machine
35B-A3B (MoE)12.3 GB downloadRuns - experts in RAM, the rest on the GPU

Mixture-of-experts: the always-on layers sit on your card, the experts sit in system memory - bigger than your card, still quick.

35B-A3B (MoE)22.1 GB downloadRuns - experts in RAM, the rest on the GPU

Mixture-of-experts: the always-on layers sit on your card, the experts sit in system memory - bigger than your card, still quick.

On Apple Silicon, system memory is also graphics memory - pick "None / integrated / Apple Silicon" and read the bars against your Mac's memory. The app checks your real hardware before every download.

Variants & sizes

VariantDownloadQuantizationNeedsApple Silicon
27B16.8 GBQ4_K_M32 GB RAMMetal (GGUF)
35B-A3B (MoE)MoE12.3 GBUD-Q2_K_XL24 GB RAMMetal (GGUF)
35B-A3B (MoE)MoE22.1 GBQ4_K_M32 GB RAMMLX · 20.7 GB

The app picks the right variant for your machine and verifies every download. Model files come straight from their official repositories, pinned to exact revisions.

License

Qwen 3.6 is released under the Apache 2.0 - read the terms. The weights download to your machine and stay there; Your Own AI adds no accounts, tracking, or lock-in on top.

Frequently asked questions

Can I run Qwen 3.6 offline?
Yes. Qwen 3.6 is a downloadable model: with Your Own AI it runs entirely on your computer, works with no internet connection, and your conversations never leave your device.
What hardware does Qwen 3.6 need?
The smallest variant (27B, a 12.3 GB download) runs on a machine with 24 GB of memory. Larger variants want more memory or a graphics card - the interactive checker on this page grades every variant against your hardware, using the same logic as the app.
Is Qwen 3.6 free to use?
The model weights are released under the Apache 2.0 license and download at no charge. Your Own AI itself is free and open source for local use.
How much context does Qwen 3.6 support?
256K tokens of context.

Run Qwen 3.6 in two clicks

Download Your Own AI, pick Qwen 3.6, and the app sizes it to your hardware. Private by architecture - no account needed for local use.