MiniCPM-V-4.7-1B on Jetson Orin NX 16GB — Q8_0, llama.cpp vision-language inference benchmark

Open this configuration in the VLM Inference Benchmark Explorer

Model	MiniCPM-V-4.7-1B
Parameters	1.6B
Device	Jetson Orin NX 16GB
Quantization	Q8_0
Image size	720p
Images per camera	1
Max Cameras (response ≤ 3 s)	>3 s
Engine	llama.cpp

Cameras	Response (s)	TPS (tok/s)	Target
1	4.26	42.7	>3 s
2	5.21	25.0	>3 s
4	15.6	25.8	>3 s
8	34.5	33.6	>3 s

Images per request	Response (s)	TPS (tok/s)	Target
1	4.26	42.7	>3 s
2	8.49	41.8	>3 s
4	17.0	39.9	>3 s
8	34.4	37.1	>3 s
16	70.0	32.1	>3 s
32	—	—	Failed

MiniCPM-V-4.7-1B (1.6B parameters), served in Q8_0 format with llama.cpp on Jetson Orin NX 16GB, starts answering a single camera that sends one 720p image after 4.26 s, then writes 42.7 tok/s.

With 16 images per camera at 720p, the answer starts after 70 s. With one 2K image, after 5.62 s.

At the default target of an answer starting within 3 s (720p, one image per camera), not even one camera is answered in time.