VLM Inference Benchmark Explorer
Qwen3-VL-8B-Instruct on Jetson AGX Orin — Q4_K_M, llama.cpp vision-language inference benchmark
Open this configuration in the VLM Inference Benchmark Explorer
| Model | Qwen3-VL-8B-Instruct |
|---|---|
| Parameters | 8.8B |
| Device | Jetson AGX Orin |
| Quantization | Q4_K_M |
| Image size | 720p |
| Images per camera | 1 |
| Max Cameras (response ≤ 3 s) | 1 |
| Engine | llama.cpp |
| Cameras | Response (s) | TPS (tok/s) | Status |
|---|---|---|---|
| 1 | 2.75 | 25.2 | PASS |
| 2 | 4.06 | 20.6 | FAIL |
| 4 | 8.56 | 14.5 | FAIL |
| 8 | 16.6 | 16.0 | FAIL |
Qwen3-VL-8B-Instruct (8.8B parameters), served in Q4_K_M format with llama.cpp on Jetson AGX Orin, starts answering a single camera that sends one 720p image after 2.75 s, then writes 25.2 tok/s.
With 5 images per camera at 720p, the answer starts after 13.24 s. With one 2K image, after 20.61 s.
At the default target of an answer starting within 3 s (720p, one image per camera), it keeps up with one camera at a time.
Qwen3-VL-8B-Instruct (8.8B parameters), served in Q4_K_M format with llama.cpp on Jetson AGX Orin, starts answering a single camera that sends one 720p image after 2.75 s, then writes 25.2 tok/s.
With 5 images per camera at 720p, the answer starts after 13.24 s. With one 2K image, after 20.61 s.
At the default target of an answer starting within 3 s (720p, one image per camera), it keeps up with one camera at a time.