Is gemma-2-9b-it-bnb-4bit or Qwen3.6-27B 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 3.0x smaller, because of how its attention layers cache.

Model comparison

gemma-2-9b-it-bnb-4bit vs Qwen3.6-27B

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

From the file· summed bytes, KV per layer

Side by side

	gemma-2-9b-it-bnb-4bit	Qwen3.6-27B
Parameters	9.5B	27.8B
Architecture	gemma2	qwen35
Layers	42	64
Native context	8,192	262,144
Mixture of experts	no	no
Quantizations published	1	40
Smallest quantization	9.15 GiB	8.74 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	gemma-2-9b-it-bnb-4bit	Qwen3.6-27B	Ratio
4,096	1.31 GiB	0.25 GiB	5.25×
8,192	2.05 GiB	0.50 GiB	4.10×
16,384	3.36 GiB	1.00 GiB	3.36×
32,768	5.99 GiB	2.00 GiB	2.99×
65,536	11.24 GiB	4.00 GiB	2.81×
131,072	21.74 GiB	8.00 GiB	2.72×