Is gemma-4-26B-A4B-it-DFlash or SmolLM2-135M-Instruct smaller?

SmolLM2-135M-Instruct is smaller at Q4_K_M: 0.10 GiB against 0.25 GiB.

Which uses less memory at long context?

gemma-4-26B-A4B-it-DFlash — its KV cache at 32K context is 4.3x smaller, because of how its attention layers cache.

Model comparison

gemma-4-26B-A4B-it-DFlash vs SmolLM2-135M-Instruct

At Q4_K_M, SmolLM2-135M-Instruct is the smaller download — 105,454,144 bytes against 266,221,536. At long context the gap widens: gemma-4-26B-A4B-it-DFlash's KV cache at 32K is 4.3× smaller, which usually matters more than the difference in weights.

From the file· summed bytes, KV per layer

Side by side

	gemma-4-26B-A4B-it-DFlash	SmolLM2-135M-Instruct
Parameters	430M	135M
Architecture	dflash	llama
Layers	5	30
Native context	262,144	8,192
Mixture of experts	no	no
Quantizations published	18	41
Smallest quantization	0.16 GiB	0.08 GiB
Q4_K_M	0.25 GiB	0.10 GiB
Licence	—	apache-2.0

KV cache by context

the term that decides long-context viability

Context	gemma-4-26B-A4B-it-DFlash	SmolLM2-135M-Instruct	Ratio
4,096	0.05 GiB	0.09 GiB	1.61×
8,192	0.07 GiB	0.18 GiB	2.50×
16,384	0.10 GiB	0.35 GiB	3.46×
32,768	0.16 GiB	0.70 GiB	4.29×
65,536	0.29 GiB	1.41 GiB	4.86×
131,072	0.54 GiB	2.81 GiB	5.22×