Is Qwen3.6-35B-A3B or EXAONE-4.5-33B smaller?

EXAONE-4.5-33B is smaller at Q4_K_M: 18.67 GiB against 19.71 GiB.

Which uses less memory at long context?

Qwen3.6-35B-A3B — its KV cache at 32K context is 4.5x smaller, because of how its attention layers cache.

Model comparison

Qwen3.6-35B-A3B vs EXAONE-4.5-33B

At Q4_K_M, EXAONE-4.5-33B is the smaller download — 20,047,839,424 bytes against 21,166,757,728. At long context the gap widens: Qwen3.6-35B-A3B's KV cache at 32K is 4.5× smaller, which usually matters more than the difference in weights.

From the file· summed bytes, KV per layer

Side by side

	Qwen3.6-35B-A3B	EXAONE-4.5-33B
Parameters	36.0B	34.4B
Architecture	qwen35moe	exaone4
Layers	40	64
Native context	262,144	262,144
Mixture of experts	yes, 256 experts	no
Quantizations published	61	31
Smallest quantization	8.77 GiB	11.57 GiB
Q4_K_M	19.71 GiB	18.67 GiB
Licence	apache-2.0	other

KV cache by context

the term that decides long-context viability

Context	Qwen3.6-35B-A3B	EXAONE-4.5-33B	Ratio
4,096	0.08 GiB	1.00 GiB	12.79×
8,192	0.16 GiB	1.34 GiB	8.60×
16,384	0.31 GiB	1.84 GiB	5.90×
32,768	0.63 GiB	2.84 GiB	4.55×
65,536	1.25 GiB	4.84 GiB	3.87×
131,072	2.50 GiB	8.84 GiB	3.54×