Model comparison

stable-diffusion-3.5-large vs Qwen-Image-Edit-2511

These two publish different quantization sets; the table below has the exact sizes.

From the file· summed bytes, KV per layer

Side by side

stable-diffusion-3.5-largeQwen-Image-Edit-2511
Parameters8.1B20.4B
Architectureqwen_image
Layers
Native context
Mixture of expertsnono
Quantizations published1736
Smallest quantization4.44 GiB4.13 GiB
Q4_K_M10.86 GiB
Licenceotherapache-2.0

KV cache by context

the term that decides long-context viability
Contextstable-diffusion-3.5-largeQwen-Image-Edit-2511Ratio
4,096
8,192
16,384
32,768
65,536
131,072