Is Gemma3-4B-CodeCenturion or Qwen3-8B smaller?

Gemma3-4B-CodeCenturion is smaller at Q4_K_M: 2.32 GiB against 4.68 GiB.

Which uses less memory at long context?

Gemma3-4B-CodeCenturion — its KV cache at 32K context is 5.7x smaller, because of how its attention layers cache.

Model comparison

Gemma3-4B-CodeCenturion vs Qwen3-8B

At Q4_K_M, Gemma3-4B-CodeCenturion is the smaller download — 2,489,761,152 bytes against 5,027,783,488. At long context the gap widens: Gemma3-4B-CodeCenturion's KV cache at 32K is 5.7× smaller, which usually matters more than the difference in weights.

From the file· summed bytes, KV per layer

Side by side

	Gemma3-4B-CodeCenturion	Qwen3-8B
Parameters	4.3B	8.2B
Architecture	gemma3	qwen3
Layers	34	36
Native context	131,072	40,960
Mixture of experts	no	no
Quantizations published	36	51
Smallest quantization	1.06 GiB	2.12 GiB
Q4_K_M	2.32 GiB	4.68 GiB
Licence	—	apache-2.0

KV cache by context

the term that decides long-context viability

Context	Gemma3-4B-CodeCenturion	Qwen3-8B	Ratio
4,096	0.25 GiB	0.56 GiB	2.27×
8,192	0.33 GiB	1.13 GiB	3.45×
16,384	0.48 GiB	2.25 GiB	4.66×
32,768	0.79 GiB	4.50 GiB	5.66×
65,536	1.42 GiB	9.00 GiB	6.34×
131,072	2.67 GiB	18.00 GiB	6.74×