VLM Inference Benchmark Explorer
Nemotron-Nano-12B-v2-VL on RTX PRO 6000 — BF16, vLLM vision-language inference benchmark
Open this configuration in the VLM Inference Benchmark Explorer
| Model | Nemotron-Nano-12B-v2-VL |
|---|---|
| Parameters | 13B |
| Device | RTX PRO 6000 |
| Quantization | BF16 |
| Image size | 720p |
| Images per camera | 1 |
| Max Cameras (TTFT ≤ 3000 ms) | 16+ |
| Engine | vLLM |
| Cameras | TTFT (ms) | TPS (tok/s) | Target |
|---|---|---|---|
| 1 | 197 | 68.5 | ≤3000 ms |
| 2 | 256 | 61.9 | ≤3000 ms |
| 4 | 251 | 56.1 | ≤3000 ms |
| 8 | 457 | 50.6 | ≤3000 ms |
| 16 | 764 | 44.4 | ≤3000 ms |
| Images per request | TTFT (ms) | TPS (tok/s) | Target |
|---|---|---|---|
| 1 | 197 | 68.5 | ≤3000 ms |
| 3 | 497 | 62.4 | ≤3000 ms |
| 5 | 777 | 64.1 | ≤3000 ms |
Nemotron-Nano-12B-v2-VL (13B parameters), served in BF16 format with vLLM on RTX PRO 6000, starts answering a single camera that sends one 720p image after 197 ms (time to first token, TTFT), then writes 68.5 tok/s.
With 5 images per camera at 720p, the answer starts after 777 ms. With one 2K image, after 612 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.
Nemotron-Nano-12B-v2-VL (13B parameters), served in BF16 format with vLLM on RTX PRO 6000, starts answering a single camera that sends one 720p image after 197 ms (time to first token, TTFT), then writes 68.5 tok/s.
With 5 images per camera at 720p, the answer starts after 777 ms. With one 2K image, after 612 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.