Is Fallen-Gemma3-27B-v1 or Qwen3.6-27B smaller?

Fallen-Gemma3-27B-v1 is smaller at Q4_K_M: 15.41 GiB against 15.41 GiB.

Which uses less memory at long context?

Qwen3.6-27B — its KV cache at 32K context is 1.2x smaller, because of how its attention layers cache.

Model comparison

Fallen-Gemma3-27B-v1 vs Qwen3.6-27B

At Q4_K_M, Fallen-Gemma3-27B-v1 is the smaller download — 16,546,688,704 bytes against 16,547,397,888. At long context the gap widens: Qwen3.6-27B's KV cache at 32K is 1.2× smaller, which usually matters more than the difference in weights.

From the file· summed bytes, KV per layer

Side by side

	Fallen-Gemma3-27B-v1	Qwen3.6-27B
Parameters	27.4B	27.8B
Architecture	gemma3	qwen35
Layers	48	64
Native context	—	262,144
Mixture of experts	no	no
Quantizations published	25	40
Smallest quantization	7.86 GiB	8.74 GiB
Q4_K_M	15.41 GiB	15.41 GiB
Licence	other	apache-2.0

KV cache by context

the term that decides long-context viability

Context	Fallen-Gemma3-27B-v1	Qwen3.6-27B	Ratio
4,096	0.67 GiB	0.25 GiB	2.69×
8,192	0.91 GiB	0.50 GiB	1.82×
16,384	1.38 GiB	1.00 GiB	1.38×
32,768	2.31 GiB	2.00 GiB	1.16×
65,536	4.19 GiB	4.00 GiB	1.05×
131,072	7.94 GiB	8.00 GiB	1.01×