VLM Inference Benchmark Explorer

Cosmos3-Edge on Jetson AGX Orin 32GB — BF16, vLLM vision-language inference benchmark

Open this configuration in the VLM Inference Benchmark Explorer

ModelCosmos3-Edge
Parameters3.9B
DeviceJetson AGX Orin 32GB
QuantizationBF16
Image size720p
Images per camera1
Max Cameras (TTFT ≤ 3000 ms)8+
EnginevLLM
CamerasTTFT (ms)TPS (tok/s)Target
168442.6≤3000 ms
280235.6≤3000 ms
4160232.0≤3000 ms
8288726.2≤3000 ms
Images per requestTTFT (ms)TPS (tok/s)Target
168442.6≤3000 ms
3175540.5≤3000 ms
5295638.5≤3000 ms

Cosmos3-Edge (3.9B parameters), served in BF16 format with vLLM on Jetson AGX Orin 32GB, starts answering a single camera that sends one 720p image after 684 ms (time to first token, TTFT), then writes 42.6 tok/s.

With 5 images per camera at 720p, the answer starts after 2,956 ms. With one 2K image, after 3,951 ms.

At the default target of a mean TTFT within 3,000 ms (720p, one image per camera), it keeps up with at least 8 cameras at once: it still met the target at the highest number measured, so the real limit is higher.