VLM Inference Benchmark Explorer

Qwen3-VL-4B-Instruct on Jetson AGX Orin 32GB — Q8_0, llama.cpp vision-language inference benchmark

Open this configuration in the VLM Inference Benchmark Explorer

ModelQwen3-VL-4B-Instruct
Parameters4.4B
DeviceJetson AGX Orin 32GB
QuantizationQ8_0
Image size720p
Images per camera1
Max Cameras (TTFT ≤ 3000 ms)2
Enginellama.cpp
CamerasTTFT (ms)TPS (tok/s)Target
1183223.2≤3000 ms
2270420.2≤3000 ms
4558414.3>3000 ms
81183912.4>3000 ms
Images per requestTTFT (ms)TPS (tok/s)Target
1183223.2≤3000 ms
3533822.5>3000 ms
5888821.8>3000 ms

Qwen3-VL-4B-Instruct (4.4B parameters), served in Q8_0 format with llama.cpp on Jetson AGX Orin 32GB, starts answering a single camera that sends one 720p image after 1,832 ms (time to first token, TTFT), then writes 23.2 tok/s.

With 5 images per camera at 720p, the answer starts after 8,888 ms. With one 2K image, after 11,276 ms.

At the default target of a mean TTFT within 3,000 ms (720p, one image per camera), it keeps up with 2 cameras at once.