Is Qwen3.5-9B or medgemma-27b-it smaller?

Qwen3.5-9B is smaller at Q4_K_M: 5.24 GiB against 15.41 GiB.

Which uses less memory at long context?

Qwen3.5-9B — its KV cache at 32K context is 3.1x smaller, because of how its attention layers cache.

Model comparison

Qwen3.5-9B vs medgemma-27b-it

At Q4_K_M, Qwen3.5-9B is the smaller download — 5,627,044,256 bytes against 16,546,689,536. At long context the gap widens: Qwen3.5-9B's KV cache at 32K is 3.1× smaller, which usually matters more than the difference in weights.

From the file· summed bytes, KV per layer

Side by side

	Qwen3.5-9B	medgemma-27b-it
Parameters	9.7B	28.8B
Architecture	qwen35	gemma3
Layers	32	62
Native context	262,144	131,072
Mixture of experts	no	no
Quantizations published	34	68
Smallest quantization	2.97 GiB	5.83 GiB
Q4_K_M	5.24 GiB	15.41 GiB
Licence	apache-2.0	other

KV cache by context

the term that decides long-context viability

Context	Qwen3.5-9B	medgemma-27b-it	Ratio
4,096	0.13 GiB	0.92 GiB	7.37×
8,192	0.25 GiB	1.23 GiB	4.94×
16,384	0.50 GiB	1.86 GiB	3.72×
32,768	1.00 GiB	3.11 GiB	3.11×
65,536	2.00 GiB	5.61 GiB	2.80×
131,072	4.00 GiB	10.61 GiB	2.65×