Is Qwen3.8-27B or Fallen-Gemma3-27B-v1 smaller?

Fallen-Gemma3-27B-v1 is smaller at Q4_K_M: 15.41 GiB against 15.66 GiB.

Which uses less memory at long context?

Qwen3.8-27B — its KV cache at 32K context is 1.2x smaller, because of how its attention layers cache.

Model comparison

Qwen3.8-27B vs Fallen-Gemma3-27B-v1

At Q4_K_M, Fallen-Gemma3-27B-v1 is the smaller download — 16,546,688,704 bytes against 16,810,714,336. At long context the gap widens: Qwen3.8-27B'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

	Qwen3.8-27B	Fallen-Gemma3-27B-v1
Parameters	27.8B	27.4B
Architecture	qwen35	gemma3
Layers	64	48
Native context	262,144	—
Mixture of experts	no	no
Quantizations published	22	25
Smallest quantization	8.39 GiB	7.86 GiB
Q4_K_M	15.66 GiB	15.41 GiB
Licence	apache-2.0	other

KV cache by context

the term that decides long-context viability

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