Granite-Vision-4.1-4B 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	Granite-Vision-4.1-4B
Parameters	4.0B
Device	Jetson AGX Orin 32GB Developer Kit
Quantization	Q8_0
Image size	720p
Images per camera	1
Max Cameras (response ≤ 3 s)	4
Engine	llama.cpp

Cameras	Response (s)	TPS (tok/s)	Target
1	1.87	28.8	≤3 s
2	1.99	13.3	≤3 s
4	2.66	12.2	≤3 s
8	12.6	14.7	>3 s

Images per request	Response (s)	TPS (tok/s)	Target
1	1.87	28.8	≤3 s
2	3.71	28.4	>3 s
4	7.49	26.8	>3 s
8	15.6	23.9	>3 s
16	34.3	19.4	>3 s
32	—	—	Failed

Granite-Vision-4.1-4B (4.0B 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 1.87 s, then writes 28.8 tok/s.

With 16 images per camera at 720p, the answer starts after 34.31 s. With one 2K image, after 2.04 s.

At the default target of an answer starting within 3 s (720p, one image per camera), it keeps up with 4 cameras at once.