Is Ministral-3-8B-Reasoning-2512-heretic or Qwen3.6-35B-A3B smaller?

Ministral-3-8B-Reasoning-2512-heretic is smaller at Q4_K_M: 4.84 GiB against 19.71 GiB.

Which uses less memory at long context?

Qwen3.6-35B-A3B — its KV cache at 32K context is 6.8x smaller, because of how its attention layers cache.

Model comparison

Ministral-3-8B-Reasoning-2512-heretic vs Qwen3.6-35B-A3B

At Q4_K_M, Ministral-3-8B-Reasoning-2512-heretic is the smaller download — 5,198,385,440 bytes against 21,166,757,728. At long context the gap widens: Qwen3.6-35B-A3B's KV cache at 32K is 6.8× smaller, which usually matters more than the difference in weights.

From the file· summed bytes, KV per layer

Side by side

	Ministral-3-8B-Reasoning-2512-heretic	Qwen3.6-35B-A3B
Parameters	8.9B	36.0B
Architecture	mistral3	qwen35moe
Layers	34	40
Native context	262,144	262,144
Mixture of experts	no	yes, 256 experts
Quantizations published	3	61
Smallest quantization	4.84 GiB	8.77 GiB
Q4_K_M	4.84 GiB	19.71 GiB
Licence	apache-2.0	apache-2.0

KV cache by context

the term that decides long-context viability

Context	Ministral-3-8B-Reasoning-2512-heretic	Qwen3.6-35B-A3B	Ratio
4,096	0.53 GiB	0.08 GiB	6.80×
8,192	1.06 GiB	0.16 GiB	6.80×
16,384	2.13 GiB	0.31 GiB	6.80×
32,768	4.25 GiB	0.63 GiB	6.80×
65,536	8.50 GiB	1.25 GiB	6.80×
131,072	17.00 GiB	2.50 GiB	6.80×