Is medgemma-1.5-4b-it or Qwen3.5-4B smaller?

medgemma-1.5-4b-it is smaller at Q4_K_M: 2.32 GiB against 2.52 GiB.

Which uses less memory at long context?

medgemma-1.5-4b-it — its KV cache at 32K context is 1.3x smaller, because of how its attention layers cache.

Model comparison

medgemma-1.5-4b-it vs Qwen3.5-4B

At Q4_K_M, medgemma-1.5-4b-it is the smaller download — 2,489,894,624 bytes against 2,707,513,696. At long context the gap widens: medgemma-1.5-4b-it's KV cache at 32K is 1.3× smaller, which usually matters more than the difference in weights.

From the file· summed bytes, KV per layer

Side by side

	medgemma-1.5-4b-it	Qwen3.5-4B
Parameters	4.3B	4.7B
Architecture	gemma3	qwen35
Layers	34	32
Native context	131,072	262,144
Mixture of experts	no	no
Quantizations published	32	57
Smallest quantization	1.10 GiB	1.42 GiB
Q4_K_M	2.32 GiB	2.52 GiB
Licence	other	apache-2.0

KV cache by context

the term that decides long-context viability

Context	medgemma-1.5-4b-it	Qwen3.5-4B	Ratio
4,096	0.25 GiB	0.13 GiB	1.98×
8,192	0.33 GiB	0.25 GiB	1.30×
16,384	0.48 GiB	0.50 GiB	1.04×
32,768	0.79 GiB	1.00 GiB	1.26×
65,536	1.42 GiB	2.00 GiB	1.41×
131,072	2.67 GiB	4.00 GiB	1.50×