VLM Inference Benchmark Explorer

Llama-3.1-Nemotron-Nano-VL-8B on RTX PRO 6000 — BF16, vLLM vision-language inference benchmark

Open this configuration in the VLM Inference Benchmark Explorer

ModelLlama-3.1-Nemotron-Nano-VL-8B
Parameters8.7B
DeviceRTX PRO 6000
QuantizationBF16
Image size720p
Images per camera1
Max Cameras (TTFT ≤ 3000 ms)16+
EnginevLLM
CamerasTTFT (ms)TPS (tok/s)Target
129294.9≤3000 ms
232584.6≤3000 ms
443173.2≤3000 ms
873559.4≤3000 ms
16127346.5≤3000 ms
Images per requestTTFT (ms)TPS (tok/s)Target
129294.9≤3000 ms
393787.8≤3000 ms
5178689.1≤3000 ms

Llama-3.1-Nemotron-Nano-VL-8B (8.7B parameters), served in BF16 format with vLLM on RTX PRO 6000, starts answering a single camera that sends one 720p image after 292 ms (time to first token, TTFT), then writes 94.9 tok/s.

With 5 images per camera at 720p, the answer starts after 1,786 ms. With one 2K image, after 486 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.