Model comparison

Qwen-Image vs Qwen-Image-Edit-2511

At Q4_K_M, Qwen-Image-Edit-2511 is the smaller download — 11,657,701,984 bytes against 13,065,746,976.

From the file· summed bytes, KV per layer

Side by side

Qwen-ImageQwen-Image-Edit-2511
Parameters20.4B20.4B
Architectureqwen_imageqwen_image
Layers
Native context
Mixture of expertsnono
Quantizations published4336
Smallest quantization6.58 GiB4.13 GiB
Q4_K_M12.17 GiB10.86 GiB
Licenceapache-2.0apache-2.0

KV cache by context

the term that decides long-context viability
ContextQwen-ImageQwen-Image-Edit-2511Ratio
4,096
8,192
16,384
32,768
65,536
131,072