Is Qwen3.6-27B or Mira-v1.12-Ties-27B smaller?

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

Which uses less memory at long context?

Qwen3.6-27B — its KV cache at 32K context is 1.6x smaller, because of how its attention layers cache.

Model comparison

Qwen3.6-27B vs Mira-v1.12-Ties-27B

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 1.6× smaller, which usually matters more than the difference in weights.

From the file· summed bytes, KV per layer

Side by side

	Qwen3.6-27B	Mira-v1.12-Ties-27B
Parameters	27.8B	27.4B
Architecture	qwen35	gemma3
Layers	64	62
Native context	262,144	131,072
Mixture of experts	no	no
Quantizations published	40	23
Smallest quantization	8.74 GiB	5.83 GiB
Q4_K_M	15.41 GiB	—
Licence	apache-2.0	—

KV cache by context

the term that decides long-context viability

Context	Qwen3.6-27B	Mira-v1.12-Ties-27B	Ratio
4,096	0.25 GiB	0.92 GiB	3.68×
8,192	0.50 GiB	1.23 GiB	2.47×
16,384	1.00 GiB	1.86 GiB	1.86×
32,768	2.00 GiB	3.11 GiB	1.55×
65,536	4.00 GiB	5.61 GiB	1.40×
131,072	8.00 GiB	10.61 GiB	1.33×