Is Qwen3.6-12B-IQ-Ultra-Heretic-Uncensored-Thinking-V2-Hightop or gemma-4-E4B-it smaller?

gemma-4-E4B-it is smaller at Q4_K_M: 4.64 GiB against 6.82 GiB.

Which uses less memory at long context?

gemma-4-E4B-it — its KV cache at 32K context is 1.5x smaller, because of how its attention layers cache.

Model comparison

Qwen3.6-12B-IQ-Ultra-Heretic-Uncensored-Thinking-V2-Hightop vs gemma-4-E4B-it

At Q4_K_M, gemma-4-E4B-it is the smaller download — 4,977,171,584 bytes against 7,323,108,608. At long context the gap widens: gemma-4-E4B-it's KV cache at 32K is 1.5× 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-E4B-it
Parameters	12.1B	8.0B
Architecture	qwen35	gemma4
Layers	24	42
Native context	262,144	131,072
Mixture of experts	no	no
Quantizations published	33	36
Smallest quantization	4.60 GiB	3.30 GiB
Q4_K_M	6.82 GiB	4.64 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-E4B-it	Ratio
4,096	0.09 GiB	0.12 GiB	1.31×
8,192	0.19 GiB	0.18 GiB	1.06×
16,384	0.38 GiB	0.29 GiB	1.31×
32,768	0.75 GiB	0.51 GiB	1.48×
65,536	1.50 GiB	0.94 GiB	1.59×
131,072	3.00 GiB	1.82 GiB	1.65×