Gemma-4-E4B-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-E4B-it
Parameters	8.0B
Device	Jetson AGX Orin 32GB Developer Kit
Quantization	Q4_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	0.86	34.2	≤3 s
2	1.36	32.4	≤3 s
4	2.69	19.2	≤3 s
8	4.91	16.9	>3 s

Images per request	Response (s)	TPS (tok/s)	Target
1	0.86	34.2	≤3 s
3	2.23	33.7	≤3 s
5	3.58	33.2	>3 s

Gemma-4-E4B-it (8.0B 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 0.86 s, then writes 34.2 tok/s.

With 5 images per camera at 720p, the answer starts after 3.58 s. With one 2K image, after 2.55 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.