VLM Inference Benchmark Explorer

Qwen3-VL-4B-Instruct on Jetson Orin NX 16GB — Q8_0, llama.cpp vision-language inference benchmark

Open this configuration in the VLM Inference Benchmark Explorer

ModelQwen3-VL-4B-Instruct
Parameters4.4B
DeviceJetson Orin NX 16GB
QuantizationQ8_0
Image size720p
Images per camera1
Max Cameras (TTFT ≤ 3000 ms)>3000 ms
Enginellama.cpp
CamerasTTFT (ms)TPS (tok/s)Target
1303714.3>3000 ms
2445214.1>3000 ms
492479.4>3000 ms
8179797.2>3000 ms
Images per requestTTFT (ms)TPS (tok/s)Target
1303714.3>3000 ms
3869613.7>3000 ms
51462313.2>3000 ms

Qwen3-VL-4B-Instruct (4.4B 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 3,037 ms (time to first token, TTFT), then writes 14.3 tok/s.

With 5 images per camera at 720p, the answer starts after 14,623 ms. With one 2K image, after 18,387 ms.

At the default target of a mean TTFT within 3,000 ms (720p, one image per camera), not even one camera is answered in time.