Is Qwen3.6-27B or Qwen3.5-99B smaller?

Qwen3.6-27B is smaller at Q4_K_M: 15.41 GiB against 56.06 GiB.

Which uses less memory at long context?

Qwen3.5-99B — its KV cache at 32K context is 2.7x smaller, because of how its attention layers cache.

Model comparison

Qwen3.6-27B vs Qwen3.5-99B

At Q4_K_M, Qwen3.6-27B is the smaller download — 16,547,397,888 bytes against 60,194,980,672. At long context the gap widens: Qwen3.5-99B's KV cache at 32K is 2.7× smaller, which usually matters more than the difference in weights.

From the file· summed bytes, KV per layer

Side by side

	Qwen3.6-27B	Qwen3.5-99B
Parameters	27.8B	99.0B
Architecture	qwen35	qwen35moe
Layers	64	48
Native context	262,144	262,144
Mixture of experts	no	yes, 205 experts
Quantizations published	40	36
Smallest quantization	8.74 GiB	19.31 GiB
Q4_K_M	15.41 GiB	56.06 GiB
Licence	apache-2.0	other

KV cache by context

the term that decides long-context viability

Context	Qwen3.6-27B	Qwen3.5-99B	Ratio
4,096	0.25 GiB	0.09 GiB	2.67×
8,192	0.50 GiB	0.19 GiB	2.67×
16,384	1.00 GiB	0.38 GiB	2.67×
32,768	2.00 GiB	0.75 GiB	2.67×
65,536	4.00 GiB	1.50 GiB	2.67×
131,072	8.00 GiB	3.00 GiB	2.67×