VLM Inference Benchmark Explorer

Qwen3.5-4B on Jetson Orin NX 16GB — Q4_K_M, llama.cpp vision-language inference benchmark

Open this configuration in the VLM Inference Benchmark Explorer

ModelQwen3.5-4B
Parameters4.7B
DeviceJetson Orin NX 16GB
QuantizationQ4_K_M
Image size720p
Images per camera1
Max Cameras (TTFT ≤ 3000 ms)>3000 ms
Enginellama.cpp
CamerasTTFT (ms)TPS (tok/s)Target
1371515.6>3000 ms
2544810.4>3000 ms
41261812.5>3000 ms
Images per requestTTFT (ms)TPS (tok/s)Target
1371515.6>3000 ms
31040215.4>3000 ms
51725015.3>3000 ms

Qwen3.5-4B (4.7B parameters), served in Q4_K_M format with llama.cpp on Jetson Orin NX 16GB, starts answering a single camera that sends one 720p image after 3,715 ms (time to first token, TTFT), then writes 15.6 tok/s.

With 5 images per camera at 720p, the answer starts after 17,250 ms. With one 1080p image, after 8,480 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.