Is Qwen3.6-27B or llama2-22b-chat-wizard-uncensored 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 16.2x smaller, because of how its attention layers cache.

Model comparison

Qwen3.6-27B vs llama2-22b-chat-wizard-uncensored

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

From the file· summed bytes, KV per layer

Side by side

	Qwen3.6-27B	llama2-22b-chat-wizard-uncensored
Parameters	27.8B	21.8B
Architecture	qwen35	llama
Layers	64	40
Native context	262,144	2,048
Mixture of experts	no	no
Quantizations published	40	2
Smallest quantization	8.74 GiB	7.56 GiB
Q4_K_M	15.41 GiB	—
Licence	apache-2.0	other

KV cache by context

the term that decides long-context viability

Context	Qwen3.6-27B	llama2-22b-chat-wizard-uncensored	Ratio
4,096	0.25 GiB	4.06 GiB	16.24×
8,192	0.50 GiB	8.13 GiB	16.24×
16,384	1.00 GiB	16.25 GiB	16.25×
32,768	2.00 GiB	32.50 GiB	16.25×
65,536	4.00 GiB	65.00 GiB	16.25×
131,072	8.00 GiB	130.00 GiB	16.25×