Is Qwen3-Coder-30B-A3B-Instruct or gemma-2-9b-it-bnb-4bit smaller?

Both publish quantizations; compare the table for the exact sizes.

Which uses less memory at long context?

Qwen3-Coder-30B-A3B-Instruct — its KV cache at 32K context is 2.0x smaller, because of how its attention layers cache.

Model comparison

Qwen3-Coder-30B-A3B-Instruct vs gemma-2-9b-it-bnb-4bit

These two publish different quantization sets; the table below has the exact sizes. At long context the gap widens: Qwen3-Coder-30B-A3B-Instruct's KV cache at 32K is 2.0× 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	gemma-2-9b-it-bnb-4bit
Parameters	30.5B	9.5B
Architecture	qwen3moe	gemma2
Layers	48	42
Native context	262,144	8,192
Mixture of experts	yes, 128 experts	no
Quantizations published	46	1
Smallest quantization	7.46 GiB	9.15 GiB
Q4_K_M	17.28 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	gemma-2-9b-it-bnb-4bit	Ratio
4,096	0.38 GiB	1.31 GiB	3.50×
8,192	0.75 GiB	2.05 GiB	2.73×
16,384	1.50 GiB	3.36 GiB	2.24×
32,768	3.00 GiB	5.99 GiB	2.00×
65,536	6.00 GiB	11.24 GiB	1.87×
131,072	12.00 GiB	21.74 GiB	1.81×