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
| Model | Qwen3-VL-4B-Instruct |
|---|---|
| Parameters | 4.4B |
| Device | Jetson Orin NX 16GB |
| Quantization | Q8_0 |
| Image size | 720p |
| Images per camera | 1 |
| Max Cameras (response ≤ 3 s) | 0 |
| Engine | llama.cpp |
| Cameras | Response (s) | TPS (tok/s) | Status |
|---|---|---|---|
| 1 | 3.04 | 14.3 | FAIL |
| 2 | 4.45 | 14.1 | FAIL |
| 4 | 9.25 | 9.4 | FAIL |
| 8 | 18.0 | 7.2 | FAIL |
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 3.04 s, then writes 14.3 tok/s.
With 5 images per camera at 720p, the answer starts after 14.62 s. With one 2K image, after 18.39 s.
At the default target of an answer starting within 3 s (720p, one image per camera), not even one camera is answered in time.
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 3.04 s, then writes 14.3 tok/s.
With 5 images per camera at 720p, the answer starts after 14.62 s. With one 2K image, after 18.39 s.
At the default target of an answer starting within 3 s (720p, one image per camera), not even one camera is answered in time.