Is Qwen3-Coder-30B-A3B-Instruct or granite-4.1-30b smaller?

granite-4.1-30b is smaller at Q4_K_M: 16.29 GiB against 17.28 GiB.

Which uses less memory at long context?

Qwen3-Coder-30B-A3B-Instruct — its KV cache at 32K context is 2.7x smaller, because of how its attention layers cache.

Model comparison

Qwen3-Coder-30B-A3B-Instruct vs granite-4.1-30b

At Q4_K_M, granite-4.1-30b is the smaller download — 17,490,240,736 bytes against 18,556,689,568. At long context the gap widens: Qwen3-Coder-30B-A3B-Instruct's KV cache at 32K is 2.7× smaller, which usually matters more than the difference in weights.

From the file· summed bytes, KV per layer

Side by side

	Qwen3-Coder-30B-A3B-Instruct	granite-4.1-30b
Parameters	30.5B	28.9B
Architecture	qwen3moe	—
Layers	48	64
Native context	262,144	131,072
Mixture of experts	yes, 128 experts	no
Quantizations published	46	18
Smallest quantization	7.46 GiB	9.99 GiB
Q4_K_M	17.28 GiB	16.29 GiB
Licence	apache-2.0	apache-2.0

KV cache by context

the term that decides long-context viability

Context	Qwen3-Coder-30B-A3B-Instruct	granite-4.1-30b	Ratio
4,096	0.38 GiB	1.00 GiB	2.67×
8,192	0.75 GiB	2.00 GiB	2.67×
16,384	1.50 GiB	4.00 GiB	2.67×
32,768	3.00 GiB	8.00 GiB	2.67×
65,536	6.00 GiB	16.00 GiB	2.67×
131,072	12.00 GiB	32.00 GiB	2.67×