Is gemma-4-12B-coder-fable5-composer2.5-v1-sft-v5-abliterated or Qwen3.6-27B smaller?

gemma-4-12B-coder-fable5-composer2.5-v1-sft-v5-abliterated is smaller at Q4_K_M: 7.98 GiB against 15.41 GiB.

Which uses less memory at long context?

Qwen3.6-27B — its KV cache at 32K context is 1.2x smaller, because of how its attention layers cache.

Model comparison

gemma-4-12B-coder-fable5-composer2.5-v1-sft-v5-abliterated vs Qwen3.6-27B

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 16,547,397,888. At long context the gap widens: Qwen3.6-27B'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

	gemma-4-12B-coder-fable5-composer2.5-v1-sft-v5-abliterated	Qwen3.6-27B
Parameters	12.0B	27.8B
Architecture	gemma4	qwen35
Layers	48	64
Native context	262,144	262,144
Mixture of experts	no	no
Quantizations published	6	40
Smallest quantization	6.77 GiB	8.74 GiB
Q4_K_M	7.98 GiB	15.41 GiB
Licence	gemma	apache-2.0

KV cache by context

the term that decides long-context viability

Context	gemma-4-12B-coder-fable5-composer2.5-v1-sft-v5-abliterated	Qwen3.6-27B	Ratio
4,096	0.72 GiB	0.25 GiB	2.87×
8,192	0.97 GiB	0.50 GiB	1.94×
16,384	1.47 GiB	1.00 GiB	1.47×
32,768	2.47 GiB	2.00 GiB	1.23×
65,536	4.47 GiB	4.00 GiB	1.12×
131,072	8.47 GiB	8.00 GiB	1.06×