Is Qwen3.6-12B-IQ-Ultra-Heretic-Uncensored-Thinking-V2-Hightop or gemma-4-12B-it-qat-q4_0-unquantized smaller?

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

Which uses less memory at long context?

Qwen3.6-12B-IQ-Ultra-Heretic-Uncensored-Thinking-V2-Hightop — its KV cache at 32K context is 3.3x smaller, because of how its attention layers cache.

Model comparison

Qwen3.6-12B-IQ-Ultra-Heretic-Uncensored-Thinking-V2-Hightop vs gemma-4-12B-it-qat-q4_0-unquantized

These two publish different quantization sets; the table below has the exact sizes. At long context the gap widens: Qwen3.6-12B-IQ-Ultra-Heretic-Uncensored-Thinking-V2-Hightop's KV cache at 32K is 3.3× smaller, which usually matters more than the difference in weights.

From the file· summed bytes, KV per layer

Side by side

	Qwen3.6-12B-IQ-Ultra-Heretic-Uncensored-Thinking-V2-Hightop	gemma-4-12B-it-qat-q4_0-unquantized
Parameters	12.1B	12.0B
Architecture	qwen35	gemma4
Layers	24	48
Native context	262,144	262,144
Mixture of experts	no	no
Quantizations published	33	2
Smallest quantization	4.60 GiB	6.50 GiB
Q4_K_M	6.82 GiB	—
Licence	apache-2.0	apache-2.0

KV cache by context

the term that decides long-context viability

Context	Qwen3.6-12B-IQ-Ultra-Heretic-Uncensored-Thinking-V2-Hightop	gemma-4-12B-it-qat-q4_0-unquantized	Ratio
4,096	0.09 GiB	0.72 GiB	7.66×
8,192	0.19 GiB	0.97 GiB	5.16×
16,384	0.38 GiB	1.47 GiB	3.92×
32,768	0.75 GiB	2.47 GiB	3.29×
65,536	1.50 GiB	4.47 GiB	2.98×
131,072	3.00 GiB	8.47 GiB	2.82×