Is Qwen3.5-2B-enko or Qwen2.5-VL-7B-Instruct smaller?

Qwen3.5-2B-enko is smaller at Q4_K_M: 1.02 GiB against 4.36 GiB.

Which uses less memory at long context?

Qwen3.5-2B-enko — its KV cache at 32K context is 4.7x smaller, because of how its attention layers cache.

Model comparison

Qwen3.5-2B-enko vs Qwen2.5-VL-7B-Instruct

At Q4_K_M, Qwen3.5-2B-enko is the smaller download — 1,100,563,648 bytes against 4,683,072,032. At long context the gap widens: Qwen3.5-2B-enko's KV cache at 32K is 4.7× smaller, which usually matters more than the difference in weights.

From the file· summed bytes, KV per layer

Side by side

	Qwen3.5-2B-enko	Qwen2.5-VL-7B-Instruct
Parameters	2.1B	8.3B
Architecture	qwen35	qwen2vl
Layers	24	28
Native context	262,144	128,000
Mixture of experts	no	no
Quantizations published	4	50
Smallest quantization	0.82 GiB	1.93 GiB
Q4_K_M	1.02 GiB	4.36 GiB
Licence	apache-2.0	apache-2.0

KV cache by context

the term that decides long-context viability

Context	Qwen3.5-2B-enko	Qwen2.5-VL-7B-Instruct	Ratio
4,096	0.05 GiB	0.22 GiB	4.66×
8,192	0.09 GiB	0.44 GiB	4.66×
16,384	0.19 GiB	0.88 GiB	4.67×
32,768	0.38 GiB	1.75 GiB	4.67×
65,536	0.75 GiB	3.50 GiB	4.67×
131,072	1.50 GiB	7.00 GiB	4.67×