Is Mistral-Small-3.2-24B-Instruct-2506 or gemma-4-12B-it smaller?

gemma-4-12B-it is smaller at Q4_K_M: 6.63 GiB against 13.35 GiB.

Which uses less memory at long context?

gemma-4-12B-it — its KV cache at 32K context is 2.0x smaller, because of how its attention layers cache.

Model comparison

Mistral-Small-3.2-24B-Instruct-2506 vs gemma-4-12B-it

At Q4_K_M, gemma-4-12B-it is the smaller download — 7,121,861,440 bytes against 14,333,909,728. At long context the gap widens: gemma-4-12B-it's KV cache at 32K is 2.0× smaller, which usually matters more than the difference in weights.

From the file· summed bytes, KV per layer

Side by side

	Mistral-Small-3.2-24B-Instruct-2506	gemma-4-12B-it
Parameters	24.0B	12.0B
Architecture	llama	gemma4
Layers	40	48
Native context	131,072	262,144
Mixture of experts	no	no
Quantizations published	50	59
Smallest quantization	5.18 GiB	3.92 GiB
Q4_K_M	13.35 GiB	6.63 GiB
Licence	apache-2.0	apache-2.0

KV cache by context

the term that decides long-context viability

Context	Mistral-Small-3.2-24B-Instruct-2506	gemma-4-12B-it	Ratio
4,096	0.63 GiB	0.72 GiB	1.15×
8,192	1.25 GiB	0.97 GiB	1.29×
16,384	2.50 GiB	1.47 GiB	1.70×
32,768	5.00 GiB	2.47 GiB	2.03×
65,536	10.00 GiB	4.47 GiB	2.24×
131,072	20.00 GiB	8.47 GiB	2.36×