Is Qwen3.6-27B or Huihui-gpt-oss-20b-BF16-abliterated smaller?

Huihui-gpt-oss-20b-BF16-abliterated is smaller at Q4_K_M: 10.87 GiB against 15.41 GiB.

Which uses less memory at long context?

Huihui-gpt-oss-20b-BF16-abliterated — its KV cache at 32K context is 2.6x smaller, because of how its attention layers cache.

Model comparison

Qwen3.6-27B vs Huihui-gpt-oss-20b-BF16-abliterated

At Q4_K_M, Huihui-gpt-oss-20b-BF16-abliterated is the smaller download — 11,673,418,400 bytes against 16,547,397,888. At long context the gap widens: Huihui-gpt-oss-20b-BF16-abliterated's KV cache at 32K is 2.6× smaller, which usually matters more than the difference in weights.

From the file· summed bytes, KV per layer

Side by side

	Qwen3.6-27B	Huihui-gpt-oss-20b-BF16-abliterated
Parameters	27.8B	20.9B
Architecture	qwen35	gpt-oss
Layers	64	24
Native context	262,144	131,072
Mixture of experts	no	yes, 32 experts
Quantizations published	40	33
Smallest quantization	8.74 GiB	10.70 GiB
Q4_K_M	15.41 GiB	10.87 GiB
Licence	apache-2.0	apache-2.0

KV cache by context

the term that decides long-context viability

Context	Qwen3.6-27B	Huihui-gpt-oss-20b-BF16-abliterated	Ratio
4,096	0.25 GiB	0.11 GiB	2.25×
8,192	0.50 GiB	0.21 GiB	2.44×
16,384	1.00 GiB	0.39 GiB	2.55×
32,768	2.00 GiB	0.77 GiB	2.61×
65,536	4.00 GiB	1.52 GiB	2.64×
131,072	8.00 GiB	3.02 GiB	2.65×