Model comparison

gemma-4-31B-it-Mystery-Fine-Tune-HERETIC-UNCENSORED-Thinking vs Qwen3.6-35B-A3B

These two publish different quantization sets; the table below has the exact sizes. At long context the gap widens: Qwen3.6-35B-A3B's KV cache at 32K is 9.9× smaller, which usually matters more than the difference in weights.

From the file· summed bytes, KV per layer

Side by side

gemma-4-31B-it-Mystery-Fine-Tune-HERETIC-UNCENSORED-ThinkingQwen3.6-35B-A3B
Parameters31.3B36.0B
Architecturegemma4qwen35moe
Layers6040
Native context262,144262,144
Mixture of expertsnoyes, 256 experts
Quantizations published2761
Smallest quantization6.66 GiB8.77 GiB
Q4_K_M19.71 GiB
Licenceapache-2.0apache-2.0

KV cache by context

the term that decides long-context viability
Contextgemma-4-31B-it-Mystery-Fine-Tune-HERETIC-UNCENSORED-ThinkingQwen3.6-35B-A3BRatio
4,0961.80 GiB0.08 GiB22.98×
8,1922.42 GiB0.16 GiB15.49×
16,3843.67 GiB0.31 GiB11.75×
32,7686.17 GiB0.63 GiB9.87×
65,53611.17 GiB1.25 GiB8.94×
131,07221.17 GiB2.50 GiB8.47×