Is Qwen3.6-27B or Nemotron-Cascade-2-30B-A3B-heretic-ara-uncensored smaller?

Qwen3.6-27B is smaller at Q4_K_M: 15.41 GiB against 22.83 GiB.

Which uses less memory at long context?

Nemotron-Cascade-2-30B-A3B-heretic-ara-uncensored — its KV cache at 32K context is 1.2x smaller, because of how its attention layers cache.

Model comparison

Qwen3.6-27B vs Nemotron-Cascade-2-30B-A3B-heretic-ara-uncensored

At Q4_K_M, Qwen3.6-27B is the smaller download — 16,547,397,888 bytes against 24,515,131,200. At long context the gap widens: Nemotron-Cascade-2-30B-A3B-heretic-ara-uncensored's KV cache at 32K is 1.2× smaller, which usually matters more than the difference in weights.

From the file· summed bytes, KV per layer

Side by side

	Qwen3.6-27B	Nemotron-Cascade-2-30B-A3B-heretic-ara-uncensored
Parameters	27.8B	31.6B
Architecture	qwen35	nemotron_h_moe
Layers	64	52
Native context	262,144	262,144
Mixture of experts	no	yes, 128 experts
Quantizations published	40	34
Smallest quantization	8.74 GiB	16.64 GiB
Q4_K_M	15.41 GiB	22.83 GiB
Licence	apache-2.0	other

KV cache by context

the term that decides long-context viability

Context	Qwen3.6-27B	Nemotron-Cascade-2-30B-A3B-heretic-ara-uncensored	Ratio
4,096	0.25 GiB	0.20 GiB	1.23×
8,192	0.50 GiB	0.41 GiB	1.23×
16,384	1.00 GiB	0.81 GiB	1.23×
32,768	2.00 GiB	1.63 GiB	1.23×
65,536	4.00 GiB	3.25 GiB	1.23×
131,072	8.00 GiB	6.50 GiB	1.23×