VLM Inference Benchmark Explorer
Qwen3.6-35B-A3B on RTX PRO 6000 — FP8, vLLM vision-language inference benchmark
Open this configuration in the VLM Inference Benchmark Explorer
| Model | Qwen3.6-35B-A3B |
|---|---|
| Parameters | 35B |
| Device | RTX PRO 6000 |
| Quantization | FP8 |
| Image size | 720p |
| Images per camera | 1 |
| Max Cameras (TTFT ≤ 3000 ms) | 16+ |
| Engine | vLLM |
| Cameras | TTFT (ms) | TPS (tok/s) | Target |
|---|---|---|---|
| 1 | 212 | 220.8 | ≤3000 ms |
| 2 | 307 | 167.0 | ≤3000 ms |
| 4 | 363 | 125.8 | ≤3000 ms |
| 8 | 499 | 116.9 | ≤3000 ms |
| 16 | 716 | 98.4 | ≤3000 ms |
| Images per request | TTFT (ms) | TPS (tok/s) | Target |
|---|---|---|---|
| 1 | 212 | 220.8 | ≤3000 ms |
| 3 | 389 | 211.5 | ≤3000 ms |
| 5 | 844 | 220.1 | ≤3000 ms |
Qwen3.6-35B-A3B (35B parameters), served in FP8 format with vLLM on RTX PRO 6000, starts answering a single camera that sends one 720p image after 212 ms (time to first token, TTFT), then writes 220.8 tok/s.
With 5 images per camera at 720p, the answer starts after 844 ms. With one 2K image, after 586 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.
Qwen3.6-35B-A3B (35B parameters), served in FP8 format with vLLM on RTX PRO 6000, starts answering a single camera that sends one 720p image after 212 ms (time to first token, TTFT), then writes 220.8 tok/s.
With 5 images per camera at 720p, the answer starts after 844 ms. With one 2K image, after 586 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.