Is Qwen3.8-27B or gemma-2-9b-it-bnb-4bit smaller?

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

Which uses less memory at long context?

Qwen3.8-27B — its KV cache at 32K context is 3.0x smaller, because of how its attention layers cache.

Model comparison

Qwen3.8-27B vs gemma-2-9b-it-bnb-4bit

These two publish different quantization sets; the table below has the exact sizes. At long context the gap widens: Qwen3.8-27B'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

	Qwen3.8-27B	gemma-2-9b-it-bnb-4bit
Parameters	27.8B	9.5B
Architecture	qwen35	gemma2
Layers	64	42
Native context	262,144	8,192
Mixture of experts	no	no
Quantizations published	22	1
Smallest quantization	8.39 GiB	9.15 GiB
Q4_K_M	15.66 GiB	—
Licence	apache-2.0	apache-2.0

KV cache by context

the term that decides long-context viability

Context	Qwen3.8-27B	gemma-2-9b-it-bnb-4bit	Ratio
4,096	0.25 GiB	1.31 GiB	5.25×
8,192	0.50 GiB	2.05 GiB	4.10×
16,384	1.00 GiB	3.36 GiB	3.36×
32,768	2.00 GiB	5.99 GiB	2.99×
65,536	4.00 GiB	11.24 GiB	2.81×
131,072	8.00 GiB	21.74 GiB	2.72×