VLM Inference Benchmark Explorer
Qwen3-VL-8B-Instruct on Jetson AGX Orin 32GB — Q8_0, 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 32GB |
| Quantization | Q8_0 |
| Image size | 720p |
| Images per camera | 1 |
| Max Cameras (response ≤ 3 s) | 1 |
| Engine | llama.cpp |
| Cameras | Response (s) | TPS (tok/s) | Status |
|---|---|---|---|
| 1 | 2.64 | 19.1 | PASS |
| 2 | 3.91 | 16.1 | FAIL |
| 4 | 7.10 | 10.0 | FAIL |
| 8 | 16.3 | 10.4 | FAIL |
Qwen3-VL-8B-Instruct (8.8B parameters), served in Q8_0 format with llama.cpp on Jetson AGX Orin 32GB, starts answering a single camera that sends one 720p image after 2.64 s, then writes 19.1 tok/s.
With 5 images per camera at 720p, the answer starts after 13.19 s. With one 2K image, after 20.48 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 Q8_0 format with llama.cpp on Jetson AGX Orin 32GB, starts answering a single camera that sends one 720p image after 2.64 s, then writes 19.1 tok/s.
With 5 images per camera at 720p, the answer starts after 13.19 s. With one 2K image, after 20.48 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.