Which uses less memory at long context?

Qwen3.6-27B — its KV cache at 32K context is 2.6x smaller, because of how its attention layers cache.

Model comparison

Qwen3.6-27B vs Qwen3-53B-A3B-2507-THINKING-TOTAL-RECALL-v2-MASTER-CODER

Q: Is Qwen3.6-27B or Qwen3-53B-A3B-2507-THINKING-TOTAL-RECALL-v2-MASTER-CODER smaller?

Both publish quantizations; compare the table for the exact sizes.

These two publish different quantization sets; the table below has the exact sizes. At long context the gap widens: Qwen3.6-27B's KV cache at 32K is 2.6× smaller, which usually matters more than the difference in weights.

From the file· summed bytes, KV per layer

Side by side

	Qwen3.6-27B	Qwen3-53B-A3B-2507-THINKING-TOTAL-RECALL-v2-MASTER-CODER
Parameters	27.8B	53.0B
Architecture	qwen35	qwen3moe
Layers	64	84
Native context	262,144	262,144
Mixture of experts	no	yes, 128 experts
Quantizations published	40	23
Smallest quantization	8.74 GiB	10.22 GiB
Q4_K_M	15.41 GiB	—
Licence	apache-2.0	apache-2.0

KV cache by context

the term that decides long-context viability

Context	Qwen3.6-27B	Qwen3-53B-A3B-2507-THINKING-TOTAL-RECALL-v2-MASTER-CODER	Ratio
4,096	0.25 GiB	0.66 GiB	2.62×
8,192	0.50 GiB	1.31 GiB	2.62×
16,384	1.00 GiB	2.63 GiB	2.62×
32,768	2.00 GiB	5.25 GiB	2.62×
65,536	4.00 GiB	10.50 GiB	2.62×
131,072	8.00 GiB	21.00 GiB	2.62×