Is gemma-4-12B-it or Ministral-3-8B-Reasoning-2512-heretic smaller?

Ministral-3-8B-Reasoning-2512-heretic is smaller at Q4_K_M: 4.84 GiB against 6.63 GiB.

Which uses less memory at long context?

gemma-4-12B-it — its KV cache at 32K context is 1.7x smaller, because of how its attention layers cache.

Model comparison

gemma-4-12B-it vs Ministral-3-8B-Reasoning-2512-heretic

At Q4_K_M, Ministral-3-8B-Reasoning-2512-heretic is the smaller download — 5,198,385,440 bytes against 7,121,861,440. At long context the gap widens: gemma-4-12B-it's KV cache at 32K is 1.7× smaller, which usually matters more than the difference in weights.

From the file· summed bytes, KV per layer

Side by side

	gemma-4-12B-it	Ministral-3-8B-Reasoning-2512-heretic
Parameters	12.0B	8.9B
Architecture	gemma4	mistral3
Layers	48	34
Native context	262,144	262,144
Mixture of experts	no	no
Quantizations published	59	3
Smallest quantization	3.92 GiB	4.84 GiB
Q4_K_M	6.63 GiB	4.84 GiB
Licence	apache-2.0	apache-2.0

KV cache by context

the term that decides long-context viability

Context	gemma-4-12B-it	Ministral-3-8B-Reasoning-2512-heretic	Ratio
4,096	0.72 GiB	0.53 GiB	1.35×
8,192	0.97 GiB	1.06 GiB	1.10×
16,384	1.47 GiB	2.13 GiB	1.45×
32,768	2.47 GiB	4.25 GiB	1.72×
65,536	4.47 GiB	8.50 GiB	1.90×
131,072	8.47 GiB	17.00 GiB	2.01×