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 (TTFT ≤ 3000 ms) | >3000 ms |
| Engine | llama.cpp |
| Cameras | TTFT (ms) | TPS (tok/s) | Target |
|---|---|---|---|
| 1 | 3037 | 14.3 | >3000 ms |
| 2 | 4452 | 14.1 | >3000 ms |
| 4 | 9247 | 9.4 | >3000 ms |
| 8 | 17979 | 7.2 | >3000 ms |
| Images per request | TTFT (ms) | TPS (tok/s) | Target |
|---|---|---|---|
| 1 | 3037 | 14.3 | >3000 ms |
| 3 | 8696 | 13.7 | >3000 ms |
| 5 | 14623 | 13.2 | >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.
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.