VLM Inference Benchmark Explorer
Qwen3-VL-8B-Instruct on RTX PRO 6000 — 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 | RTX PRO 6000 |
| Quantization | Q8_0 |
| Image size | 720p |
| Images per camera | 1 |
| Max Cameras (TTFT ≤ 3000 ms) | 16+ |
| Engine | llama.cpp |
| Cameras | TTFT (ms) | TPS (tok/s) | Target |
|---|---|---|---|
| 1 | 329 | 153.8 | ≤3000 ms |
| 2 | 391 | 101.8 | ≤3000 ms |
| 4 | 611 | 62.0 | ≤3000 ms |
| 8 | 1294 | 75.2 | ≤3000 ms |
| 16 | 2032 | 56.3 | ≤3000 ms |
| Images per request | TTFT (ms) | TPS (tok/s) | Target |
|---|---|---|---|
| 1 | 329 | 153.8 | ≤3000 ms |
| 3 | 725 | 151.5 | ≤3000 ms |
| 5 | 1037 | 146.1 | ≤3000 ms |
Qwen3-VL-8B-Instruct (8.8B parameters), served in Q8_0 format with llama.cpp on RTX PRO 6000, starts answering a single camera that sends one 720p image after 329 ms (time to first token, TTFT), then writes 153.8 tok/s.
With 5 images per camera at 720p, the answer starts after 1,037 ms. With one 2K image, after 1,788 ms.
At the default target of a mean TTFT within 3,000 ms (720p, one image per camera), it keeps up with at least 16 cameras at once: it still met the target at the highest number measured, so the real limit is higher.
Qwen3-VL-8B-Instruct (8.8B parameters), served in Q8_0 format with llama.cpp on RTX PRO 6000, starts answering a single camera that sends one 720p image after 329 ms (time to first token, TTFT), then writes 153.8 tok/s.
With 5 images per camera at 720p, the answer starts after 1,037 ms. With one 2K image, after 1,788 ms.
At the default target of a mean TTFT within 3,000 ms (720p, one image per camera), it keeps up with at least 16 cameras at once: it still met the target at the highest number measured, so the real limit is higher.