Model comparison

gemma-4-26B-roleplay-v2-merged vs Qwen-AgentWorld-35B-A3B

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

From the file· summed bytes, KV per layer

Side by side

gemma-4-26B-roleplay-v2-mergedQwen-AgentWorld-35B-A3B
Parameters25.2B34.7B
Architecturegemma4qwen35moe
Layers40
Native context262,144
Mixture of expertsnoyes, 256 experts
Quantizations published3415
Smallest quantization7.72 GiB10.71 GiB
Q4_K_M15.64 GiB
Licenceapache-2.0

KV cache by context

the term that decides long-context viability
Contextgemma-4-26B-roleplay-v2-mergedQwen-AgentWorld-35B-A3BRatio
4,0960.08 GiB
8,1920.16 GiB
16,3840.31 GiB
32,7680.63 GiB
65,5361.25 GiB
131,0722.50 GiB