Is magnum-v4-22b or Qwen3-Coder-30B-A3B-Instruct smaller?

magnum-v4-22b is smaller at Q4_K_M: 12.42 GiB against 17.28 GiB.

Which uses less memory at long context?

Qwen3-Coder-30B-A3B-Instruct — its KV cache at 32K context is 2.3x smaller, because of how its attention layers cache.

Model comparison

magnum-v4-22b vs Qwen3-Coder-30B-A3B-Instruct

At Q4_K_M, magnum-v4-22b is the smaller download — 13,341,242,144 bytes against 18,556,689,568. At long context the gap widens: Qwen3-Coder-30B-A3B-Instruct's KV cache at 32K is 2.3× smaller, which usually matters more than the difference in weights.

From the file· summed bytes, KV per layer

Side by side

	magnum-v4-22b	Qwen3-Coder-30B-A3B-Instruct
Parameters	22.2B	30.5B
Architecture	llama	qwen3moe
Layers	56	48
Native context	32,768	262,144
Mixture of experts	no	yes, 128 experts
Quantizations published	43	46
Smallest quantization	4.50 GiB	7.46 GiB
Q4_K_M	12.42 GiB	17.28 GiB
Licence	other	apache-2.0

KV cache by context

the term that decides long-context viability

Context	magnum-v4-22b	Qwen3-Coder-30B-A3B-Instruct	Ratio
4,096	0.88 GiB	0.38 GiB	2.33×
8,192	1.75 GiB	0.75 GiB	2.33×
16,384	3.50 GiB	1.50 GiB	2.33×
32,768	7.00 GiB	3.00 GiB	2.33×
65,536	14.00 GiB	6.00 GiB	2.33×
131,072	28.00 GiB	12.00 GiB	2.33×