Qwen3-VL-8B-Instruct 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	Qwen3-VL-8B-Instruct
Parameters	8.8B
Device	Jetson AGX Orin 32GB Developer Kit
Quantization	Q4_K_M
Image size	720p
Images per camera	1
Max Cameras (response ≤ 3 s)	1
Engine	llama.cpp

Cameras	Response (s)	TPS (tok/s)	Target
1	2.75	25.2	≤3 s
2	4.06	20.6	>3 s
4	8.56	14.5	>3 s
8	16.6	16.0	>3 s

Images per request	Response (s)	TPS (tok/s)	Target
1	2.75	25.2	≤3 s
3	7.98	24.2	>3 s
5	13.2	23.4	>3 s

Qwen3-VL-8B-Instruct (8.8B 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 2.75 s, then writes 25.2 tok/s.

With 5 images per camera at 720p, the answer starts after 13.24 s. With one 2K image, after 20.61 s.

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