Hugging FaceFor editing a photo: add or remove an object, or rewrite its Chinese or English words in the same font.
- Parameters
- 20B
- Download
- 19 to 31 GB
- Commercial use
- Yes
Too big for this Mac
Its smallest size needs 21 GB of memory, more than M4 · 16 GB can give it.
Pictures made with Qwen Image Edit
See allThe rest are this month's best-liked on Civitai, shown from there; each belongs to the person who made it. Open one for its maker.
About
It can combine several photos in one edit, such as a person with a product or a scene. Besides rewriting the words in a picture, it can change their font, colour and material.
Good to know
Qwen's team used it to make emoji packs of their capybara mascot, themed on personality types.
Writing text was taught in stages, from simple words up to whole paragraphs.
Combining photos was added later by training it further on images joined together.
Sources: Qwen/Qwen-Image-Edit-2509 model card, Qwen-Image Technical Report, Qwen-Image-Edit: Image Editing with Higher Quality and Efficiency | Qwen. Every line comes from one of these.
Good at
Licence
Apache 2.0. Commercial use: yes. The maker's page has the full terms.
Qwen Image Edit runs well from a Mac with an M1 Pro and 32 GB of memory, at Q4_K_M. 40 of 59 Mac configurations run it well.
Compare with
The nearest models in size, judged for the same Mac.
Sizes
Memory is what llama.cpp's own calculator reported for each size when the catalog was built, with the app's settings. Smaller, Balanced and Best are the three sizes the store names.
Run It Anywhere
Qwen Image Edit is an open model. For ComfyUI, with the ComfyUI-GGUF nodes installed, put one of the GGUF files in ComfyUI/models/unet.
- ComfyUIWindows, Linux, Mac
Files
On every Mac
| Mac | Size | Fit | Memory |
|---|---|---|---|
| M6 · 16 GB | Q4_K_M | Too big | 21 GB |
| M6 · 24 GB | Q4_K_M | Too big | 21 GB |
| M6 · 32 GB | Q4_K_M | Runs well | 21 GB |
| M5 · 16 GB | Q4_K_M | Too big | 21 GB |
| M5 · 24 GB | Q4_K_M | Too big | 21 GB |
| M5 · 32 GB | Q4_K_M | Runs well | 21 GB |
| M5 Pro · 24 GB | Q4_K_M | Too big | 21 GB |
| M5 Pro · 48 GB | Q4_K_M | Runs great | 21 GB |
| M5 Pro · 64 GB | Q4_K_M | Runs great | 21 GB |
| M5 Max · 36 GB | Q4_K_M | Runs well | 21 GB |
| M5 Max · 48 GB | Q4_K_M | Runs great | 21 GB |
| M5 Max · 64 GB | Q4_K_M | Runs great | 21 GB |
| M5 Max · 128 GB | Q8_0 | Runs great | 33 GB |
| M5 Ultra · 96 GB | Q8_0 | Runs great | 33 GB |
| M5 Ultra · 256 GB | Q8_0 | Runs great | 33 GB |
| M5 Ultra · 512 GB | Q8_0 | Runs great | 33 GB |
| M4 · 16 GB | Q4_K_M | Too big | 21 GB |
| M4 · 24 GB | Q4_K_M | Too big | 21 GB |
| M4 · 32 GB | Q4_K_M | Runs well | 21 GB |
| M4 Pro · 24 GB | Q4_K_M | Too big | 21 GB |
| M4 Pro · 48 GB | Q4_K_M | Runs great | 21 GB |
| M4 Pro · 64 GB | Q4_K_M | Runs great | 21 GB |
| M4 Max · 36 GB | Q4_K_M | Runs well | 21 GB |
| M4 Max · 48 GB | Q4_K_M | Runs great | 21 GB |
| M4 Max · 64 GB | Q4_K_M | Runs great | 21 GB |
| M4 Max · 96 GB | Q8_0 | Runs great | 33 GB |
| M4 Max · 128 GB | Q8_0 | Runs great | 33 GB |
| M3 · 8 GB | Q4_K_M | Too big | 21 GB |
| M3 · 16 GB | Q4_K_M | Too big | 21 GB |
| M3 · 24 GB | Q4_K_M | Too big | 21 GB |
| M3 Pro · 18 GB | Q4_K_M | Too big | 21 GB |
| M3 Pro · 36 GB | Q4_K_M | Runs well | 21 GB |
| M3 Max · 36 GB | Q4_K_M | Runs well | 21 GB |
| M3 Max · 48 GB | Q4_K_M | Runs great | 21 GB |
| M3 Max · 64 GB | Q4_K_M | Runs great | 21 GB |
| M3 Max · 96 GB | Q8_0 | Runs great | 33 GB |
| M3 Max · 128 GB | Q8_0 | Runs great | 33 GB |
| M3 Ultra · 96 GB | Q8_0 | Runs great | 33 GB |
| M3 Ultra · 256 GB | Q8_0 | Runs great | 33 GB |
| M3 Ultra · 512 GB | Q8_0 | Runs great | 33 GB |
| M2 · 8 GB | Q4_K_M | Too big | 21 GB |
| M2 · 16 GB | Q4_K_M | Too big | 21 GB |
| M2 · 24 GB | Q4_K_M | Too big | 21 GB |
| M2 Pro · 16 GB | Q4_K_M | Too big | 21 GB |
| M2 Pro · 32 GB | Q4_K_M | Runs well | 21 GB |
| M2 Max · 32 GB | Q4_K_M | Runs well | 21 GB |
| M2 Max · 64 GB | Q4_K_M | Runs great | 21 GB |
| M2 Max · 96 GB | Q8_0 | Runs great | 33 GB |
| M2 Ultra · 64 GB | Q4_K_M | Runs great | 21 GB |
| M2 Ultra · 128 GB | Q8_0 | Runs great | 33 GB |
| M2 Ultra · 192 GB | Q8_0 | Runs great | 33 GB |
| M1 · 8 GB | Q4_K_M | Too big | 21 GB |
| M1 · 16 GB | Q4_K_M | Too big | 21 GB |
| M1 Pro · 16 GB | Q4_K_M | Too big | 21 GB |
| M1 Pro · 32 GB | Q4_K_M | Runs well | 21 GB |
| M1 Max · 32 GB | Q4_K_M | Runs well | 21 GB |
| M1 Max · 64 GB | Q4_K_M | Runs great | 21 GB |
| M1 Ultra · 64 GB | Q4_K_M | Runs great | 21 GB |
| M1 Ultra · 128 GB | Q8_0 | Runs great | 33 GB |
The size is the one the store offers that Mac. Constants fitted October 11, 2026; how, and how wrong.
Badge for the model card
Shows on Qwen Image Edit's Hugging Face card which Macs run it well, linked to this page. It updates every morning.
Sizes and files are read from QuantStack/Qwen-Image-Edit-2509-GGUF on Hugging Face and checked every morning. Catalog of November 4, 2026.