VLM Inference Benchmark Explorer
Qwen3-VL-4B-Instruct on Jetson Orin NX 16GB — FP8, vLLM vision-language inference benchmark
Open this configuration in the VLM Inference Benchmark Explorer
| Model | Qwen3-VL-4B-Instruct |
|---|---|
| Parameters | 4.4B |
| Device | Jetson Orin NX 16GB |
| Quantization | FP8 |
| Image size | 720p |
| Images per camera | 1 |
| Max Cameras (TTFT ≤ 3000 ms) | 2 |
| Engine | vLLM |
| Cameras | TTFT (ms) | TPS (tok/s) | Target |
|---|---|---|---|
| 1 | 1668 | 14.2 | ≤3000 ms |
| 2 | 2590 | 13.1 | ≤3000 ms |
| 4 | 4744 | 13.1 | >3000 ms |
| Images per request | TTFT (ms) | TPS (tok/s) | Target |
|---|---|---|---|
| 1 | 1668 | 14.2 | ≤3000 ms |
| 3 | 4004 | 14.2 | >3000 ms |
Qwen3-VL-4B-Instruct (4.4B parameters), served in FP8 format with vLLM on Jetson Orin NX 16GB, starts answering a single camera that sends one 720p image after 1,668 ms (time to first token, TTFT), then writes 14.2 tok/s.
With 3 images per camera at 720p, the answer starts after 4,004 ms. With one 1080p image, after 4,345 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.
Qwen3-VL-4B-Instruct (4.4B parameters), served in FP8 format with vLLM on Jetson Orin NX 16GB, starts answering a single camera that sends one 720p image after 1,668 ms (time to first token, TTFT), then writes 14.2 tok/s.
With 3 images per camera at 720p, the answer starts after 4,004 ms. With one 1080p image, after 4,345 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.