Is Qwen3.8-27B or granite-4.0-h-small smaller?

Qwen3.8-27B is smaller at Q4_K_M: 15.66 GiB against 18.14 GiB.

Which uses less memory at long context?

granite-4.0-h-small — its KV cache at 32K context is 4.0x smaller, because of how its attention layers cache.

Model comparison

Qwen3.8-27B vs granite-4.0-h-small

At Q4_K_M, Qwen3.8-27B is the smaller download — 16,810,714,336 bytes against 19,476,621,984. At long context the gap widens: granite-4.0-h-small's KV cache at 32K is 4.0× smaller, which usually matters more than the difference in weights.

From the file· summed bytes, KV per layer

Side by side

	Qwen3.8-27B	granite-4.0-h-small
Parameters	27.8B	32.2B
Architecture	qwen35	granitehybrid
Layers	64	40
Native context	262,144	131,072
Mixture of experts	no	yes, 72 experts
Quantizations published	22	41
Smallest quantization	8.39 GiB	7.59 GiB
Q4_K_M	15.66 GiB	18.14 GiB
Licence	apache-2.0	—

KV cache by context

the term that decides long-context viability

Context	Qwen3.8-27B	granite-4.0-h-small	Ratio
4,096	0.25 GiB	0.06 GiB	3.99×
8,192	0.50 GiB	0.13 GiB	4.00×
16,384	1.00 GiB	0.25 GiB	4.00×
32,768	2.00 GiB	0.50 GiB	4.00×
65,536	4.00 GiB	1.00 GiB	4.00×
131,072	8.00 GiB	2.00 GiB	4.00×