Qwen-Drive-1.0-4B on Jetson Orin NX 16GB — Q8_0, llama.cpp vision-language inference benchmark

Open this configuration in the VLM Inference Benchmark Explorer

Model	Qwen-Drive-1.0-4B
Parameters	4.5B
Device	Jetson Orin NX 16GB
Quantization	Q8_0
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	3.35	11.8	>3 s
2	6.63	13.8	>3 s
4	21.1	13.9	>3 s
8	46.2	13.8	>3 s

Images per request	Response (s)	TPS (tok/s)	Target
1	3.35	11.8	>3 s
2	6.42	11.7	>3 s
4	12.6	11.5	>3 s
8	25.1	11.1	>3 s
16	50.8	10.5	>3 s
32	105.0	9.4	>3 s

Qwen-Drive-1.0-4B (4.5B parameters), served in Q8_0 format with llama.cpp on Jetson Orin NX 16GB, starts answering a single camera that sends one 720p image after 3.35 s, then writes 11.8 tok/s.

With 32 images per camera at 720p, the answer starts after 105.02 s. With one 2K image, after 19.48 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.