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

gemma-2-9b-it-abliterated is smaller at Q4_K_M: 5.37 GiB against 17.28 GiB.

Which uses less memory at long context?

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

Model comparison

Qwen3-Coder-30B-A3B-Instruct vs gemma-2-9b-it-abliterated

At Q4_K_M, gemma-2-9b-it-abliterated is the smaller download — 5,761,057,760 bytes against 18,556,689,568. 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-abliterated
Parameters	30.5B	9.2B
Architecture	qwen3moe	gemma2
Layers	48	42
Native context	262,144	8,192
Mixture of experts	yes, 128 experts	no
Quantizations published	46	20
Smallest quantization	7.46 GiB	3.20 GiB
Q4_K_M	17.28 GiB	5.37 GiB
Licence	apache-2.0	gemma

KV cache by context

the term that decides long-context viability

Context	Qwen3-Coder-30B-A3B-Instruct	gemma-2-9b-it-abliterated	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×