Alibaba Qwen · First MLX build 23 May 2026
Qwen-Image-Edit-2511
MLX
Image apache-2.0
A 20B parameter image to image model from Alibaba Qwen, with 2 MLX builds, from bf16 to 8-bit.
- Parameters
- 20B From Hugging Face
- Quantisation
- bf16 TeleStyleV2-Qwen-Image-Edit-2511-bf16
- Memory needed
- 48 GB Estimate, unified memory
- Download
- 40.9 GB Weights, estimated
- Downloads
- 23 This build, last 30 days
- Task
- Image to image Image
- MLX builds
- 2 On mlx-community
- Devices
- Mac Apple silicon
Memory
Will it fit?Needs about 48 GB at bf16
8 GB
16 GB
24 GB
32 GB
64 GB
128 GB
Fits with headroomTight, close other appsWon’t fit
Estimated from the size of the weights, plus a fifth for context and working memory and 2 GB for macOS and your apps. Long contexts need more.
Run it
Terminal · Hugging Face CLI$ pip install -U huggingface_hub
$ hf download mlx-community/TeleStyleV2-Qwen-Image-Edit-2511-bf16MLX builds
2 on mlx-community| TeleStyleV2-Qwen-Image-Edit-2511-bf16 | bf16 | 40.9 GB | 48 GB | 23 |
|---|---|---|---|---|
| qwen-image-edit-2511-8bit | 8-bit | — | — | 0 |
Sizes are estimated from Hugging Face’s parameter counts and the quantisation. Downloads are for the last 30 days.