Is gemma-4-19b-a4b-it-REAP-heretic or Qwen3.8-27B smaller?

gemma-4-19b-a4b-it-REAP-heretic is smaller at Q4_K_M: 9.38 GiB against 15.66 GiB.

Which uses less memory at long context?

gemma-4-19b-a4b-it-REAP-heretic — its KV cache at 32K context is 1.3x smaller, because of how its attention layers cache.

Model comparison

gemma-4-19b-a4b-it-REAP-heretic vs Qwen3.8-27B

At Q4_K_M, gemma-4-19b-a4b-it-REAP-heretic is the smaller download — 10,069,118,784 bytes against 16,810,714,336. At long context the gap widens: gemma-4-19b-a4b-it-REAP-heretic's KV cache at 32K is 1.3× smaller, which usually matters more than the difference in weights.

From the file· summed bytes, KV per layer

Side by side

	gemma-4-19b-a4b-it-REAP-heretic	Qwen3.8-27B
Parameters	19.0B	27.8B
Architecture	gemma4	qwen35
Layers	30	64
Native context	262,144	262,144
Mixture of experts	yes, 90 experts	no
Quantizations published	27	22
Smallest quantization	5.70 GiB	8.39 GiB
Q4_K_M	9.38 GiB	15.66 GiB
Licence	gemma	apache-2.0

KV cache by context

the term that decides long-context viability

Context	gemma-4-19b-a4b-it-REAP-heretic	Qwen3.8-27B	Ratio
4,096	0.45 GiB	0.25 GiB	1.80×
8,192	0.61 GiB	0.50 GiB	1.21×
16,384	0.92 GiB	1.00 GiB	1.09×
32,768	1.54 GiB	2.00 GiB	1.30×
65,536	2.79 GiB	4.00 GiB	1.43×
131,072	5.29 GiB	8.00 GiB	1.51×