Is Qwen3-Coder-30B-A3B-Instruct or gemma-4-12B-coder-fable5-composer2.5-v1-sft-v5-abliterated smaller?

gemma-4-12B-coder-fable5-composer2.5-v1-sft-v5-abliterated is smaller at Q4_K_M: 7.98 GiB against 17.28 GiB.

Which uses less memory at long context?

gemma-4-12B-coder-fable5-composer2.5-v1-sft-v5-abliterated — its KV cache at 32K context is 1.2x smaller, because of how its attention layers cache.

Model comparison

Qwen3-Coder-30B-A3B-Instruct vs gemma-4-12B-coder-fable5-composer2.5-v1-sft-v5-abliterated

At Q4_K_M, gemma-4-12B-coder-fable5-composer2.5-v1-sft-v5-abliterated is the smaller download — 8,568,877,696 bytes against 18,556,689,568. At long context the gap widens: gemma-4-12B-coder-fable5-composer2.5-v1-sft-v5-abliterated's KV cache at 32K is 1.2× 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-4-12B-coder-fable5-composer2.5-v1-sft-v5-abliterated
Parameters	30.5B	12.0B
Architecture	qwen3moe	gemma4
Layers	48	48
Native context	262,144	262,144
Mixture of experts	yes, 128 experts	no
Quantizations published	46	6
Smallest quantization	7.46 GiB	6.77 GiB
Q4_K_M	17.28 GiB	7.98 GiB
Licence	apache-2.0	gemma

KV cache by context

the term that decides long-context viability

Context	Qwen3-Coder-30B-A3B-Instruct	gemma-4-12B-coder-fable5-composer2.5-v1-sft-v5-abliterated	Ratio
4,096	0.38 GiB	0.72 GiB	1.92×
8,192	0.75 GiB	0.97 GiB	1.29×
16,384	1.50 GiB	1.47 GiB	1.02×
32,768	3.00 GiB	2.47 GiB	1.22×
65,536	6.00 GiB	4.47 GiB	1.34×
131,072	12.00 GiB	8.47 GiB	1.42×