Is Qwen3.6-35B-A3B-DFlash or Qwen2.5-0.5B-Instruct smaller?

Qwen3.6-35B-A3B-DFlash is smaller at Q4_K_M: 0.22 GiB against 0.37 GiB.

Which uses less memory at long context?

Qwen3.6-35B-A3B-DFlash — its KV cache at 32K context is 1.8x smaller, because of how its attention layers cache.

Model comparison

Qwen3.6-35B-A3B-DFlash vs Qwen2.5-0.5B-Instruct

At Q4_K_M, Qwen3.6-35B-A3B-DFlash is the smaller download — 235,691,744 bytes against 397,807,936. At long context the gap widens: Qwen3.6-35B-A3B-DFlash's KV cache at 32K is 1.8× 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	Qwen2.5-0.5B-Instruct
Parameters	386M	494M
Architecture	dflash	qwen2
Layers	6	24
Native context	262,144	32,768
Mixture of experts	no	no
Quantizations published	18	32
Smallest quantization	0.14 GiB	0.31 GiB
Q4_K_M	0.22 GiB	0.37 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	Qwen2.5-0.5B-Instruct	Ratio
4,096	0.09 GiB	0.05 GiB	2.00×
8,192	0.12 GiB	0.09 GiB	1.27×
16,384	0.15 GiB	0.19 GiB	1.25×
32,768	0.21 GiB	0.38 GiB	1.76×
65,536	0.34 GiB	0.75 GiB	2.22×
131,072	0.59 GiB	1.50 GiB	2.55×