Model comparison

Qwen3.6-27B-Fable-Fusion-711-Uncensored-Heretic-NM-DAU-MTP vs diffusiongemma-26B-A4B-it

At Q4_K_M, diffusiongemma-26B-A4B-it is the smaller download — 16,806,810,208 bytes against 36,545,830,912. At long context the gap widens: diffusiongemma-26B-A4B-it's KV cache at 32K is 1.3× smaller, which usually matters more than the difference in weights.

From the file· summed bytes, KV per layer

Side by side

Qwen3.6-27B-Fable-Fusion-711-Uncensored-Heretic-NM-DAU-MTPdiffusiongemma-26B-A4B-it
Parameters27.8B25.8B
Architectureqwen35diffusion-gemma
Layers6430
Native context262,144262,144
Mixture of expertsnoyes, 128 experts
Quantizations published3412
Smallest quantization10.12 GiB9.86 GiB
Q4_K_M34.04 GiB15.65 GiB
Licenceapache-2.0apache-2.0

KV cache by context

the term that decides long-context viability
ContextQwen3.6-27B-Fable-Fusion-711-Uncensored-Heretic-NM-DAU-MTPdiffusiongemma-26B-A4B-itRatio
4,0960.25 GiB0.45 GiB1.80×
8,1920.50 GiB0.61 GiB1.21×
16,3841.00 GiB0.92 GiB1.09×
32,7682.00 GiB1.54 GiB1.30×
65,5364.00 GiB2.79 GiB1.43×
131,0728.00 GiB5.29 GiB1.51×