Is magnum-v4-27b or Qwen3.6-27B smaller?

Qwen3.6-27B is smaller at Q4_K_M: 15.41 GiB against 15.50 GiB.

Which uses less memory at long context?

Qwen3.6-27B — its KV cache at 32K context is 3.3x smaller, because of how its attention layers cache.

Model comparison

magnum-v4-27b vs Qwen3.6-27B

At Q4_K_M, Qwen3.6-27B is the smaller download — 16,547,397,888 bytes against 16,645,381,728. At long context the gap widens: Qwen3.6-27B's KV cache at 32K is 3.3× smaller, which usually matters more than the difference in weights.

From the file· summed bytes, KV per layer

Side by side

	magnum-v4-27b	Qwen3.6-27B
Parameters	27.2B	27.8B
Architecture	gemma2	qwen35
Layers	46	64
Native context	8,192	262,144
Mixture of experts	no	no
Quantizations published	22	40
Smallest quantization	7.82 GiB	8.74 GiB
Q4_K_M	15.50 GiB	15.41 GiB
Licence	gemma	apache-2.0

KV cache by context

the term that decides long-context viability

Context	magnum-v4-27b	Qwen3.6-27B	Ratio
4,096	1.44 GiB	0.25 GiB	5.75×
8,192	2.25 GiB	0.50 GiB	4.49×
16,384	3.68 GiB	1.00 GiB	3.68×
32,768	6.56 GiB	2.00 GiB	3.28×
65,536	12.31 GiB	4.00 GiB	3.08×
131,072	23.81 GiB	8.00 GiB	2.98×