Is Qwen3.6-27B or gemma-2-9b smaller?

gemma-2-9b is smaller at Q4_K_M: 5.37 GiB against 15.41 GiB.

Which uses less memory at long context?

Qwen3.6-27B — its KV cache at 32K context is 3.0x smaller, because of how its attention layers cache.

Model comparison

Qwen3.6-27B vs gemma-2-9b

At Q4_K_M, gemma-2-9b is the smaller download — 5,761,057,664 bytes against 16,547,397,888. At long context the gap widens: Qwen3.6-27B's KV cache at 32K is 3.0× smaller, which usually matters more than the difference in weights.

From the file· summed bytes, KV per layer

Side by side

	Qwen3.6-27B	gemma-2-9b
Parameters	27.8B	9.2B
Architecture	qwen35	gemma2
Layers	64	42
Native context	262,144	8,192
Mixture of experts	no	no
Quantizations published	40	18
Smallest quantization	8.74 GiB	3.54 GiB
Q4_K_M	15.41 GiB	5.37 GiB
Licence	apache-2.0	gemma

KV cache by context

the term that decides long-context viability

Context	Qwen3.6-27B	gemma-2-9b	Ratio
4,096	0.25 GiB	1.31 GiB	5.25×
8,192	0.50 GiB	2.05 GiB	4.10×
16,384	1.00 GiB	3.36 GiB	3.36×
32,768	2.00 GiB	5.99 GiB	2.99×
65,536	4.00 GiB	11.24 GiB	2.81×
131,072	8.00 GiB	21.74 GiB	2.72×