Is magnum-v4-27b or Qwen3-Coder-30B-A3B-Instruct smaller?

magnum-v4-27b is smaller at Q4_K_M: 15.50 GiB against 17.28 GiB.

Which uses less memory at long context?

Qwen3-Coder-30B-A3B-Instruct — its KV cache at 32K context is 2.2x smaller, because of how its attention layers cache.

Model comparison

magnum-v4-27b vs Qwen3-Coder-30B-A3B-Instruct

At Q4_K_M, magnum-v4-27b is the smaller download — 16,645,381,728 bytes against 18,556,689,568. At long context the gap widens: Qwen3-Coder-30B-A3B-Instruct's KV cache at 32K is 2.2× 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-Coder-30B-A3B-Instruct
Parameters	27.2B	30.5B
Architecture	gemma2	qwen3moe
Layers	46	48
Native context	8,192	262,144
Mixture of experts	no	yes, 128 experts
Quantizations published	22	46
Smallest quantization	7.82 GiB	7.46 GiB
Q4_K_M	15.50 GiB	17.28 GiB
Licence	gemma	apache-2.0

KV cache by context

the term that decides long-context viability

Context	magnum-v4-27b	Qwen3-Coder-30B-A3B-Instruct	Ratio
4,096	1.44 GiB	0.38 GiB	3.83×
8,192	2.25 GiB	0.75 GiB	2.99×
16,384	3.68 GiB	1.50 GiB	2.46×
32,768	6.56 GiB	3.00 GiB	2.19×
65,536	12.31 GiB	6.00 GiB	2.05×
131,072	23.81 GiB	12.00 GiB	1.98×