VLM Inference Benchmark Explorer

MedGemma-1.5-4B-it on RTX PRO 6000 — BF16, vLLM vision-language inference benchmark

Open this configuration in the VLM Inference Benchmark Explorer

ModelMedGemma-1.5-4B-it
Parameters4.3B
DeviceRTX PRO 6000
QuantizationBF16
Image size720p
Images per camera1
Max Cameras (TTFT ≤ 3000 ms)16+
EnginevLLM
CamerasTTFT (ms)TPS (tok/s)Target
1199171.5≤3000 ms
2159165.1≤3000 ms
4160154.0≤3000 ms
8224143.2≤3000 ms
16399134.1≤3000 ms
Images per requestTTFT (ms)TPS (tok/s)Target
1199171.5≤3000 ms
3264171.5≤3000 ms
5447170.0≤3000 ms

MedGemma-1.5-4B-it (4.3B parameters), served in BF16 format with vLLM on RTX PRO 6000, starts answering a single camera that sends one 720p image after 199 ms (time to first token, TTFT), then writes 171.5 tok/s.

With 5 images per camera at 720p, the answer starts after 447 ms. With one 2K image, after 249 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.