Is gemma-4-31B-it-Mystery-Fine-Tune-HERETIC-UNCENSORED-Thinking or Qwen3.6-27B-Fable-Fusion-711-Uncensored-Heretic-NM-DAU-MTP smaller?

Both publish quantizations; compare the table for the exact sizes.

Which uses less memory at long context?

Qwen3.6-27B-Fable-Fusion-711-Uncensored-Heretic-NM-DAU-MTP — its KV cache at 32K context is 3.1x smaller, because of how its attention layers cache.

Model comparison

gemma-4-31B-it-Mystery-Fine-Tune-HERETIC-UNCENSORED-Thinking vs Qwen3.6-27B-Fable-Fusion-711-Uncensored-Heretic-NM-DAU-MTP

These two publish different quantization sets; the table below has the exact sizes. At long context the gap widens: Qwen3.6-27B-Fable-Fusion-711-Uncensored-Heretic-NM-DAU-MTP's KV cache at 32K is 3.1× 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-Thinking	Qwen3.6-27B-Fable-Fusion-711-Uncensored-Heretic-NM-DAU-MTP
Parameters	31.3B	27.8B
Architecture	gemma4	qwen35
Layers	60	64
Native context	262,144	262,144
Mixture of experts	no	no
Quantizations published	27	34
Smallest quantization	6.66 GiB	10.12 GiB
Q4_K_M	—	34.04 GiB
Licence	apache-2.0	apache-2.0

KV cache by context

the term that decides long-context viability

Context	gemma-4-31B-it-Mystery-Fine-Tune-HERETIC-UNCENSORED-Thinking	Qwen3.6-27B-Fable-Fusion-711-Uncensored-Heretic-NM-DAU-MTP	Ratio
4,096	1.80 GiB	0.25 GiB	7.18×
8,192	2.42 GiB	0.50 GiB	4.84×
16,384	3.67 GiB	1.00 GiB	3.67×
32,768	6.17 GiB	2.00 GiB	3.09×
65,536	11.17 GiB	4.00 GiB	2.79×
131,072	21.17 GiB	8.00 GiB	2.65×