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

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

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

	Qwen3.6-27B-Fable-Fusion-711-Uncensored-Heretic-NM-DAU-MTP	gemma-4-31B-it-Mystery-Fine-Tune-HERETIC-UNCENSORED-Thinking
Parameters	27.8B	31.3B
Architecture	qwen35	gemma4
Layers	64	60
Native context	262,144	262,144
Mixture of experts	no	no
Quantizations published	34	27
Smallest quantization	10.12 GiB	6.66 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	Qwen3.6-27B-Fable-Fusion-711-Uncensored-Heretic-NM-DAU-MTP	gemma-4-31B-it-Mystery-Fine-Tune-HERETIC-UNCENSORED-Thinking	Ratio
4,096	0.25 GiB	1.80 GiB	7.18×
8,192	0.50 GiB	2.42 GiB	4.84×
16,384	1.00 GiB	3.67 GiB	3.67×
32,768	2.00 GiB	6.17 GiB	3.09×
65,536	4.00 GiB	11.17 GiB	2.79×
131,072	8.00 GiB	21.17 GiB	2.65×