Is EXAONE-4.0-32B or Qwen3.6-27B smaller?

Qwen3.6-27B is smaller at Q4_K_M: 15.41 GiB against 18.02 GiB.

Which uses less memory at long context?

Qwen3.6-27B — its KV cache at 32K context is 1.4x smaller, because of how its attention layers cache.

Model comparison

EXAONE-4.0-32B vs Qwen3.6-27B

At Q4_K_M, Qwen3.6-27B is the smaller download — 16,547,397,888 bytes against 19,343,826,720. At long context the gap widens: Qwen3.6-27B's KV cache at 32K is 1.4× smaller, which usually matters more than the difference in weights.

From the file· summed bytes, KV per layer

Side by side

	EXAONE-4.0-32B	Qwen3.6-27B
Parameters	32.0B	27.8B
Architecture	exaone4	qwen35
Layers	64	64
Native context	131,072	262,144
Mixture of experts	no	no
Quantizations published	31	40
Smallest quantization	8.96 GiB	8.74 GiB
Q4_K_M	18.02 GiB	15.41 GiB
Licence	other	apache-2.0

KV cache by context

the term that decides long-context viability

Context	EXAONE-4.0-32B	Qwen3.6-27B	Ratio
4,096	1.00 GiB	0.25 GiB	4.00×
8,192	1.34 GiB	0.50 GiB	2.69×
16,384	1.84 GiB	1.00 GiB	1.84×
32,768	2.84 GiB	2.00 GiB	1.42×
65,536	4.84 GiB	4.00 GiB	1.21×
131,072	8.84 GiB	8.00 GiB	1.11×