MiniCPM-V-4.7-1B on Jetson AGX Orin 32GB Developer Kit — 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 AGX Orin 32GB Developer Kit
Quantization	Q8_0
Image size	720p
Images per camera	1
Max Cameras (response ≤ 3 s)	2
Engine	llama.cpp

Cameras	Response (s)	TPS (tok/s)	Target
1	1.92	76.8	≤3 s
2	2.12	34.2	≤3 s
4	4.55	27.5	>3 s
8	12.6	25.5	>3 s

Images per request	Response (s)	TPS (tok/s)	Target
1	1.92	76.8	≤3 s
2	3.78	76.3	>3 s
4	7.48	73.5	>3 s
8	15.0	68.9	>3 s
16	30.4	60.5	>3 s
32	—	—	Failed

MiniCPM-V-4.7-1B (1.6B parameters), served in Q8_0 format with llama.cpp on Jetson AGX Orin 32GB Developer Kit, starts answering a single camera that sends one 720p image after 1.92 s, then writes 76.8 tok/s.

With 16 images per camera at 720p, the answer starts after 30.4 s. With one 2K image, after 2.59 s.

At the default target of an answer starting within 3 s (720p, one image per camera), it keeps up with 2 cameras at once.