Model comparison

diffusiongemma-26B-A4B-it vs Qwen3.6-35B-A3B

At Q4_K_M, diffusiongemma-26B-A4B-it is the smaller download — 16,806,810,208 bytes against 21,166,757,728. At long context the gap widens: Qwen3.6-35B-A3B's KV cache at 32K is 2.5× smaller, which usually matters more than the difference in weights.

From the file· summed bytes, KV per layer

Side by side

diffusiongemma-26B-A4B-itQwen3.6-35B-A3B
Parameters25.8B36.0B
Architecturediffusion-gemmaqwen35moe
Layers3040
Native context262,144262,144
Mixture of expertsyes, 128 expertsyes, 256 experts
Quantizations published1261
Smallest quantization9.86 GiB8.77 GiB
Q4_K_M15.65 GiB19.71 GiB
Licenceapache-2.0apache-2.0

KV cache by context

the term that decides long-context viability
Contextdiffusiongemma-26B-A4B-itQwen3.6-35B-A3BRatio
4,0960.45 GiB0.08 GiB5.75×
8,1920.61 GiB0.16 GiB3.87×
16,3840.92 GiB0.31 GiB2.94×
32,7681.54 GiB0.63 GiB2.47×
65,5362.79 GiB1.25 GiB2.23×
131,0725.29 GiB2.50 GiB2.12×