Is Qwen3-VL-2B-Instruct or MiniCPM-V-4.6 smaller?

MiniCPM-V-4.6 is smaller at Q4_K_M: 0.49 GiB against 1.03 GiB.

Which uses less memory at long context?

MiniCPM-V-4.6 — its KV cache at 32K context is 9.3x smaller, because of how its attention layers cache.

Model comparison

Qwen3-VL-2B-Instruct vs MiniCPM-V-4.6

At Q4_K_M, MiniCPM-V-4.6 is the smaller download — 529,101,504 bytes against 1,107,409,952. At long context the gap widens: MiniCPM-V-4.6's KV cache at 32K is 9.3× smaller, which usually matters more than the difference in weights.

From the file· summed bytes, KV per layer

Side by side

	Qwen3-VL-2B-Instruct	MiniCPM-V-4.6
Parameters	2.1B	1.3B
Architecture	qwen3vl	qwen35
Layers	28	24
Native context	262,144	262,144
Mixture of experts	no	no
Quantizations published	46	15
Smallest quantization	0.50 GiB	0.47 GiB
Q4_K_M	1.03 GiB	0.49 GiB
Licence	apache-2.0	apache-2.0

KV cache by context

the term that decides long-context viability

Context	Qwen3-VL-2B-Instruct	MiniCPM-V-4.6	Ratio
4,096	0.44 GiB	0.05 GiB	9.33×
8,192	0.88 GiB	0.09 GiB	9.33×
16,384	1.75 GiB	0.19 GiB	9.33×
32,768	3.50 GiB	0.38 GiB	9.33×
65,536	7.00 GiB	0.75 GiB	9.33×
131,072	14.00 GiB	1.50 GiB	9.33×