Model comparison

Chroma vs Qwen-Image-Edit-2511

At Q4_K_M, Chroma is the smaller download — 5,566,533,792 bytes against 11,657,701,984.

From the file· summed bytes, KV per layer

Side by side

ChromaQwen-Image-Edit-2511
Parameters8.9B20.4B
Architecturefluxqwen_image
Layers
Native context
Mixture of expertsnono
Quantizations published27336
Smallest quantization3.99 GiB4.13 GiB
Q4_K_M5.18 GiB10.86 GiB
Licenceapache-2.0apache-2.0

KV cache by context

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