Hugging FaceFor making pictures with readable words in them, in English or Chinese.
- Parameters
- 20B
- Download
- 18 to 30 GB
- Commercial use
- Yes
Too big for this Mac
Its smallest size needs 20 GB of memory, more than M4 · 16 GB can give it.
Pictures made with Qwen Image
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
Built so that words are blended into the picture rather than laid on top of it. It works in many styles, from photo-real scenes and impressionist paintings to anime and minimalist design. When editing, it was made to keep both the meaning and the look of the original picture.
Good to know
It was trained in stages, from pictures without text to simple text, then complex text.
Sources: Qwen/Qwen-Image model card, Qwen-Image Technical Report, Qwen-Image Technical Report. 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 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 is an open model. Draw Things and DiffusionBee take it from Qwen's own files on Hugging Face. For ComfyUI, with the ComfyUI-GGUF nodes installed, put one of the GGUF files in ComfyUI/models/unet.
Open
Open
Files
On every Mac
| Mac | Size | Fit | Memory |
|---|---|---|---|
| M6 · 16 GB | Q4_K_M | Too big | 20 GB |
| M6 · 24 GB | Q4_K_M | Too big | 20 GB |
| M6 · 32 GB | Q4_K_M | Runs well | 20 GB |
| M5 · 16 GB | Q4_K_M | Too big | 20 GB |
| M5 · 24 GB | Q4_K_M | Too big | 20 GB |
| M5 · 32 GB | Q4_K_M | Runs well | 20 GB |
| M5 Pro · 24 GB | Q4_K_M | Too big | 20 GB |
| M5 Pro · 48 GB | Q4_K_M | Runs great | 20 GB |
| M5 Pro · 64 GB | Q4_K_M | Runs great | 20 GB |
| M5 Max · 36 GB | Q4_K_M | Runs well | 20 GB |
| M5 Max · 48 GB | Q4_K_M | Runs great | 20 GB |
| M5 Max · 64 GB | Q4_K_M | Runs great | 20 GB |
| M5 Max · 128 GB | Q8_0 | Runs great | 32 GB |
| M5 Ultra · 96 GB | Q8_0 | Runs great | 32 GB |
| M5 Ultra · 256 GB | Q8_0 | Runs great | 32 GB |
| M5 Ultra · 512 GB | Q8_0 | Runs great | 32 GB |
| M4 · 16 GB | Q4_K_M | Too big | 20 GB |
| M4 · 24 GB | Q4_K_M | Too big | 20 GB |
| M4 · 32 GB | Q4_K_M | Runs well | 20 GB |
| M4 Pro · 24 GB | Q4_K_M | Too big | 20 GB |
| M4 Pro · 48 GB | Q4_K_M | Runs great | 20 GB |
| M4 Pro · 64 GB | Q4_K_M | Runs great | 20 GB |
| M4 Max · 36 GB | Q4_K_M | Runs well | 20 GB |
| M4 Max · 48 GB | Q4_K_M | Runs great | 20 GB |
| M4 Max · 64 GB | Q4_K_M | Runs great | 20 GB |
| M4 Max · 96 GB | Q8_0 | Runs great | 32 GB |
| M4 Max · 128 GB | Q8_0 | Runs great | 32 GB |
| M3 · 8 GB | Q4_K_M | Too big | 20 GB |
| M3 · 16 GB | Q4_K_M | Too big | 20 GB |
| M3 · 24 GB | Q4_K_M | Too big | 20 GB |
| M3 Pro · 18 GB | Q4_K_M | Too big | 20 GB |
| M3 Pro · 36 GB | Q4_K_M | Runs well | 20 GB |
| M3 Max · 36 GB | Q4_K_M | Runs well | 20 GB |
| M3 Max · 48 GB | Q4_K_M | Runs great | 20 GB |
| M3 Max · 64 GB | Q4_K_M | Runs great | 20 GB |
| M3 Max · 96 GB | Q8_0 | Runs great | 32 GB |
| M3 Max · 128 GB | Q8_0 | Runs great | 32 GB |
| M3 Ultra · 96 GB | Q8_0 | Runs great | 32 GB |
| M3 Ultra · 256 GB | Q8_0 | Runs great | 32 GB |
| M3 Ultra · 512 GB | Q8_0 | Runs great | 32 GB |
| M2 · 8 GB | Q4_K_M | Too big | 20 GB |
| M2 · 16 GB | Q4_K_M | Too big | 20 GB |
| M2 · 24 GB | Q4_K_M | Too big | 20 GB |
| M2 Pro · 16 GB | Q4_K_M | Too big | 20 GB |
| M2 Pro · 32 GB | Q4_K_M | Runs well | 20 GB |
| M2 Max · 32 GB | Q4_K_M | Runs well | 20 GB |
| M2 Max · 64 GB | Q4_K_M | Runs great | 20 GB |
| M2 Max · 96 GB | Q8_0 | Runs great | 32 GB |
| M2 Ultra · 64 GB | Q4_K_M | Runs great | 20 GB |
| M2 Ultra · 128 GB | Q8_0 | Runs great | 32 GB |
| M2 Ultra · 192 GB | Q8_0 | Runs great | 32 GB |
| M1 · 8 GB | Q4_K_M | Too big | 20 GB |
| M1 · 16 GB | Q4_K_M | Too big | 20 GB |
| M1 Pro · 16 GB | Q4_K_M | Too big | 20 GB |
| M1 Pro · 32 GB | Q4_K_M | Runs well | 20 GB |
| M1 Max · 32 GB | Q4_K_M | Runs well | 20 GB |
| M1 Max · 64 GB | Q4_K_M | Runs great | 20 GB |
| M1 Ultra · 64 GB | Q4_K_M | Runs great | 20 GB |
| M1 Ultra · 128 GB | Q8_0 | Runs great | 32 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'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-GGUF on Hugging Face and checked every morning. Catalog of November 4, 2026.