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 (TTFT ≤ 3000 ms) | >3000 ms |
| Engine | llama.cpp |
| Cameras | TTFT (ms) | TPS (tok/s) | Target |
|---|---|---|---|
| 1 | 3868 | 17.0 | >3000 ms |
| 2 | 5839 | 12.8 | >3000 ms |
| 4 | 12205 | 9.6 | >3000 ms |
| 8 | 21287 | 6.2 | >3000 ms |
| Images per request | TTFT (ms) | TPS (tok/s) | Target |
|---|---|---|---|
| 1 | 3868 | 17.0 | >3000 ms |
| 3 | 11512 | 16.6 | >3000 ms |
| 5 | 19204 | 16.2 | >3000 ms |
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 3,868 ms (time to first token, TTFT), then writes 17 tok/s.
With 5 images per camera at 720p, the answer starts after 19,204 ms. With one 2K image, after 31,317 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-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 3,868 ms (time to first token, TTFT), then writes 17 tok/s.
With 5 images per camera at 720p, the answer starts after 19,204 ms. With one 2K image, after 31,317 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.