Pre-quantized, MLX-ready repackagings of Qwen/Qwen-Image-Edit-2511 for the SceneWorks native Apple-Silicon worker (mlx-gen). Each tier is a complete, self-contained turnkey snapshot that loads directly with no in-app conversion peak (epic 8506).

Tier	Subdir	What's packed	Approx. size
Q4	`q4/`	transformer packed to 4-bit (group 64); dense bf16 TE + VAE	~26 GB
Q8	`q8/`	transformer packed to 8-bit (group 64); dense bf16 TE + VAE	~36 GB
bf16	`bf16/`	dense bf16 transformer + TE + VAE (full precision)	~55 GB

Only the transformer is quantized. The Qwen2.5-VL text encoder is skip_quantization (quantization degrades its semantics) and the VAE is all-convolution (no quantizable leaves), so both stay dense bf16 in every tier. Q4/Q8 use plain asymmetric group-affine quantization (group size 64), byte-identical to the worker's load-time quantization.

This repo also backs qwen_image_edit_2511_lightning (same checkpoint, Lightning-distilled sampling).

License & attribution

Apache License 2.0, inherited from the upstream Qwen-Image-Edit-2511 release. The model weights are © Alibaba Cloud / the Qwen team; this repository only re-packages them (quantization + MLX layout) and adds no new training. See LICENSE. Original model card: https://huggingface.co/Qwen/Qwen-Image-Edit-2511

SceneWorks/qwen-image-edit-2511-mlx

Qwen-Image-Edit-2511 — MLX quant matrix (bf16 / Q8 / Q4)

License & attribution

SceneWorks/
qwen-image-edit-2511-mlx