Model comparison

Illustrious-xl-early-release-v0 vs Qwen-Image-Edit-2511

At Q4_K_M, Illustrious-xl-early-release-v0 is the smaller download — 6,109,905,792 bytes against 11,657,701,984.

From the file· summed bytes, KV per layer

Side by side

Illustrious-xl-early-release-v0Qwen-Image-Edit-2511
Parameters2.6B20.4B
Architecturesdxlqwen_image
Layers
Native context
Mixture of expertsnono
Quantizations published1536
Smallest quantization3.30 GiB4.13 GiB
Q4_K_M5.69 GiB10.86 GiB
Licenceapache-2.0apache-2.0

KV cache by context

the term that decides long-context viability
ContextIllustrious-xl-early-release-v0Qwen-Image-Edit-2511Ratio
4,096
8,192
16,384
32,768
65,536
131,072