Model comparison

DreamOmni2 vs Qwen-Image-Edit-2511

At Q4_K_M, DreamOmni2 is the smaller download — 4,683,071,936 bytes against 11,657,701,984.

From the file· summed bytes, KV per layer

Side by side

DreamOmni2Qwen-Image-Edit-2511
Parameters7.6B20.4B
Architectureqwen2vlqwen_image
Layers
Native context
Mixture of expertsnono
Quantizations published1236
Smallest quantization2.81 GiB4.13 GiB
Q4_K_M4.36 GiB10.86 GiB
Licenceapache-2.0apache-2.0

KV cache by context

the term that decides long-context viability
ContextDreamOmni2Qwen-Image-Edit-2511Ratio
4,096
8,192
16,384
32,768
65,536
131,072