Is Qwen3.6-27B or OpenMedResearch-Gemma-4E4N smaller?

OpenMedResearch-Gemma-4E4N is smaller at Q4_K_M: 4.97 GiB against 15.41 GiB.

Which uses less memory at long context?

OpenMedResearch-Gemma-4E4N — its KV cache at 32K context is 4.0x smaller, because of how its attention layers cache.

Model comparison

Qwen3.6-27B vs OpenMedResearch-Gemma-4E4N

At Q4_K_M, OpenMedResearch-Gemma-4E4N is the smaller download — 5,335,277,024 bytes against 16,547,397,888. At long context the gap widens: OpenMedResearch-Gemma-4E4N's KV cache at 32K is 4.0× smaller, which usually matters more than the difference in weights.

From the file· summed bytes, KV per layer

Side by side

	Qwen3.6-27B	OpenMedResearch-Gemma-4E4N
Parameters	27.8B	8.0B
Architecture	qwen35	gemma4
Layers	64	42
Native context	262,144	131,072
Mixture of experts	no	no
Quantizations published	40	28
Smallest quantization	8.74 GiB	4.10 GiB
Q4_K_M	15.41 GiB	4.97 GiB
Licence	apache-2.0	—

KV cache by context

the term that decides long-context viability

Context	Qwen3.6-27B	OpenMedResearch-Gemma-4E4N	Ratio
4,096	0.25 GiB	0.12 GiB	2.03×
8,192	0.50 GiB	0.18 GiB	2.81×
16,384	1.00 GiB	0.29 GiB	3.48×
32,768	2.00 GiB	0.51 GiB	3.95×
65,536	4.00 GiB	0.94 GiB	4.24×
131,072	8.00 GiB	1.82 GiB	4.40×