Gemma-4-26B-A4B-it on Jetson AGX Orin 32GB Developer Kit — Q4_0, llama.cpp vision-language inference benchmark

Open this configuration in the VLM Inference Benchmark Explorer

Model	Gemma-4-26B-A4B-it
Parameters	26B
Device	Jetson AGX Orin 32GB Developer Kit
Quantization	Q4_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	2.34	32.7	≤3 s
2	2.81	14.6	≤3 s
4	6.07	9.4	>3 s
8	15.6	10.2	>3 s

Images per request	Response (s)	TPS (tok/s)	Target
1	2.34	32.7	≤3 s
3	6.60	30.2	>3 s
5	10.8	30.7	>3 s

Gemma-4-26B-A4B-it (26B parameters), served in Q4_0 format with llama.cpp on Jetson AGX Orin 32GB Developer Kit, starts answering a single camera that sends one 720p image after 2.34 s, then writes 32.7 tok/s.

With 5 images per camera at 720p, the answer starts after 10.78 s. With one 2K image, after 9.94 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.