Is gemma-3-4b-it-roleplay-tuned-v2 or Llama-3.1-8B-Instruct smaller?

gemma-3-4b-it-roleplay-tuned-v2 is smaller at Q4_K_M: 2.32 GiB against 4.58 GiB.

Which uses less memory at long context?

gemma-3-4b-it-roleplay-tuned-v2 — its KV cache at 32K context is 5.0x smaller, because of how its attention layers cache.

Model comparison

gemma-3-4b-it-roleplay-tuned-v2 vs Llama-3.1-8B-Instruct

At Q4_K_M, gemma-3-4b-it-roleplay-tuned-v2 is the smaller download — 2,489,894,848 bytes against 4,920,739,168. At long context the gap widens: gemma-3-4b-it-roleplay-tuned-v2's KV cache at 32K is 5.0× smaller, which usually matters more than the difference in weights.

From the file· summed bytes, KV per layer

Side by side

	gemma-3-4b-it-roleplay-tuned-v2	Llama-3.1-8B-Instruct
Parameters	4.3B	8.0B
Architecture	gemma3	llama
Layers	34	32
Native context	131,072	131,072
Mixture of experts	no	no
Quantizations published	36	45
Smallest quantization	1.06 GiB	2.02 GiB
Q4_K_M	2.32 GiB	4.58 GiB
Licence	gemma	llama3.1

KV cache by context

the term that decides long-context viability

Context	gemma-3-4b-it-roleplay-tuned-v2	Llama-3.1-8B-Instruct	Ratio
4,096	0.25 GiB	0.50 GiB	2.02×
8,192	0.33 GiB	1.00 GiB	3.07×
16,384	0.48 GiB	2.00 GiB	4.15×
32,768	0.79 GiB	4.00 GiB	5.03×
65,536	1.42 GiB	8.00 GiB	5.63×
131,072	2.67 GiB	16.00 GiB	5.99×