Is Macaron-V1-Tall or Qwen3.8-27B smaller?

Qwen3.8-27B is smaller at Q4_K_M: 15.66 GiB against 19.72 GiB.

Which uses less memory at long context?

Macaron-V1-Tall — its KV cache at 32K context is 3.2x smaller, because of how its attention layers cache.

Model comparison

Macaron-V1-Tall vs Qwen3.8-27B

At Q4_K_M, Qwen3.8-27B is the smaller download — 16,810,714,336 bytes against 21,169,117,568. At long context the gap widens: Macaron-V1-Tall's KV cache at 32K is 3.2× smaller, which usually matters more than the difference in weights.

From the file· summed bytes, KV per layer

Side by side

	Macaron-V1-Tall	Qwen3.8-27B
Parameters	36.0B	27.8B
Architecture	qwen35moe	qwen35
Layers	40	64
Native context	262,144	262,144
Mixture of experts	yes, 256 experts	no
Quantizations published	1	22
Smallest quantization	19.72 GiB	8.39 GiB
Q4_K_M	19.72 GiB	15.66 GiB
Licence	other	apache-2.0

KV cache by context

the term that decides long-context viability

Context	Macaron-V1-Tall	Qwen3.8-27B	Ratio
4,096	0.08 GiB	0.25 GiB	3.20×
8,192	0.16 GiB	0.50 GiB	3.20×
16,384	0.31 GiB	1.00 GiB	3.20×
32,768	0.63 GiB	2.00 GiB	3.20×
65,536	1.25 GiB	4.00 GiB	3.20×
131,072	2.50 GiB	8.00 GiB	3.20×