Picture published by the creator on Hugging Face.

Run Qwen’s image model on your laptop, compressed

Made by Unsloth AI

Unsloth’s release repackages Qwen-Image-2.1 — the open image-generation model — into GGUF files, the compact format that runs on ordinary computers through tools like llama.cpp and Stable Diffusion.cpp instead of demanding a datacenter GPU.

Several compression levels are offered, from near-lossless down to tiny, and Unsloth says its per-layer precision tuning keeps quality close to the original. Note the download is the image denoiser only: you also need the VAE and the Qwen3-VL text-encoder files, which Unsloth links from the same page. The model stays under its own license terms, which the hub lists as non-standard.

Can I use this?

Runs with llama.cpp-style tools on your computer

You'll need llama.cpp or Stable Diffusion.cpp, plus the VAE and text-encoder files · Setup needed

Worth knowing Quality claims are Unsloth’s own. Heavily compressed builds can differ from the original in ways benchmarks do not show. The hub lists the license as “other” — read the model page before commercial use. BuildTube has not run or verified this model.

Why it's here

317 people have liked it on Hugging Face.
It was downloaded 352,549 times in the last 30 days.

Numbers from the snapshot taken 1 October 2026; not refreshed since.

Behind it

See the code on Hugging Face

BuildTube has not run or verified this project. Everything above is written from what the creator published.

Made this?