Is Qwen3.5-9B-Neo or gemma-4-31B-it smaller?

Qwen3.5-9B-Neo is smaller at Q4_K_M: 5.50 GiB against 17.07 GiB.

Which uses less memory at long context?

Qwen3.5-9B-Neo — its KV cache at 32K context is 6.2x smaller, because of how its attention layers cache.

Model comparison

Qwen3.5-9B-Neo vs gemma-4-31B-it

At Q4_K_M, Qwen3.5-9B-Neo is the smaller download — 5,910,779,968 bytes against 18,323,733,440. At long context the gap widens: Qwen3.5-9B-Neo's KV cache at 32K is 6.2× smaller, which usually matters more than the difference in weights.

From the file· summed bytes, KV per layer

Side by side

	Qwen3.5-9B-Neo	gemma-4-31B-it
Parameters	9.7B	31.3B
Architecture	qwen35	gemma4
Layers	32	60
Native context	262,144	262,144
Mixture of experts	no	no
Quantizations published	24	55
Smallest quantization	3.36 GiB	7.95 GiB
Q4_K_M	5.50 GiB	17.07 GiB
Licence	apache-2.0	apache-2.0

KV cache by context

the term that decides long-context viability

Context	Qwen3.5-9B-Neo	gemma-4-31B-it	Ratio
4,096	0.13 GiB	1.80 GiB	14.36×
8,192	0.25 GiB	2.42 GiB	9.68×
16,384	0.50 GiB	3.67 GiB	7.34×
32,768	1.00 GiB	6.17 GiB	6.17×
65,536	2.00 GiB	11.17 GiB	5.59×
131,072	4.00 GiB	21.17 GiB	5.29×