Is Gemma-3-27B-MeditronFO or Qwen3.6-27B smaller?

Qwen3.6-27B is smaller at Q4_K_M: 15.41 GiB against 16.15 GiB.

Which uses less memory at long context?

Qwen3.6-27B — its KV cache at 32K context is 1.6x smaller, because of how its attention layers cache.

Model comparison

Gemma-3-27B-MeditronFO vs Qwen3.6-27B

At Q4_K_M, Qwen3.6-27B is the smaller download — 16,547,397,888 bytes against 17,339,606,784. At long context the gap widens: Qwen3.6-27B's KV cache at 32K is 1.6× smaller, which usually matters more than the difference in weights.

From the file· summed bytes, KV per layer

Side by side

	Gemma-3-27B-MeditronFO	Qwen3.6-27B
Parameters	28.8B	27.8B
Architecture	gemma3	qwen35
Layers	62	64
Native context	—	262,144
Mixture of experts	no	no
Quantizations published	34	40
Smallest quantization	6.26 GiB	8.74 GiB
Q4_K_M	16.15 GiB	15.41 GiB
Licence	gemma	apache-2.0

KV cache by context

the term that decides long-context viability

Context	Gemma-3-27B-MeditronFO	Qwen3.6-27B	Ratio
4,096	0.92 GiB	0.25 GiB	3.68×
8,192	1.23 GiB	0.50 GiB	2.47×
16,384	1.86 GiB	1.00 GiB	1.86×
32,768	3.11 GiB	2.00 GiB	1.55×
65,536	5.61 GiB	4.00 GiB	1.40×
131,072	10.61 GiB	8.00 GiB	1.33×