Is Qwen3.6-35B-A3B-DFlash or SmolLM2-135M-Instruct smaller?

SmolLM2-135M-Instruct is smaller at Q4_K_M: 0.10 GiB against 0.22 GiB.

Which uses less memory at long context?

Qwen3.6-35B-A3B-DFlash — its KV cache at 32K context is 3.3x smaller, because of how its attention layers cache.

Model comparison

Qwen3.6-35B-A3B-DFlash vs SmolLM2-135M-Instruct

At Q4_K_M, SmolLM2-135M-Instruct is the smaller download — 105,454,144 bytes against 235,691,744. At long context the gap widens: Qwen3.6-35B-A3B-DFlash's KV cache at 32K is 3.3× smaller, which usually matters more than the difference in weights.

From the file· summed bytes, KV per layer

Side by side

	Qwen3.6-35B-A3B-DFlash	SmolLM2-135M-Instruct
Parameters	386M	135M
Architecture	dflash	llama
Layers	6	30
Native context	262,144	8,192
Mixture of experts	no	no
Quantizations published	18	41
Smallest quantization	0.14 GiB	0.08 GiB
Q4_K_M	0.22 GiB	0.10 GiB
Licence	apache-2.0	apache-2.0

KV cache by context

the term that decides long-context viability

Context	Qwen3.6-35B-A3B-DFlash	SmolLM2-135M-Instruct	Ratio
4,096	0.09 GiB	0.09 GiB	1.07×
8,192	0.12 GiB	0.18 GiB	1.48×
16,384	0.15 GiB	0.35 GiB	2.34×
32,768	0.21 GiB	0.70 GiB	3.30×
65,536	0.34 GiB	1.41 GiB	4.16×
131,072	0.59 GiB	2.81 GiB	4.78×