MiniCPM-V-4.7-35B-A3B on Jetson AGX Orin 32GB Developer Kit — Q4_K_M, llama.cpp vision-language inference benchmark

Open this configuration in the VLM Inference Benchmark Explorer

Model	MiniCPM-V-4.7-35B-A3B
Parameters	35B
Device	Jetson AGX Orin 32GB Developer Kit
Quantization	Q4_K_M
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	3.55	34.8	>3 s
2	5.72	18.3	>3 s
4	12.0	17.6	>3 s
8	30.3	19.5	>3 s

Images per request	Response (s)	TPS (tok/s)	Target
1	3.55	34.8	>3 s
2	6.95	34.0	>3 s
4	13.8	32.4	>3 s
8	27.7	29.6	>3 s
16	56.7	25.5	>3 s
32	—	—	Failed

MiniCPM-V-4.7-35B-A3B (35B parameters), served in Q4_K_M format with llama.cpp on Jetson AGX Orin 32GB Developer Kit, starts answering a single camera that sends one 720p image after 3.55 s, then writes 34.8 tok/s.

With 16 images per camera at 720p, the answer starts after 56.67 s. With one 2K image, after 4.84 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.