VLM Inference Benchmark Explorer

Alpamayo2-Super on Jetson AGX Thor — BF16, vLLM vision-language inference benchmark

Open this configuration in the VLM Inference Benchmark Explorer

ModelAlpamayo2-Super
Parameters34.3B
DeviceJetson AGX Thor
QuantizationBF16
Image size720p
Images per camera1
Max Cameras (TTFT ≤ 3000 ms)16
EnginevLLM
CamerasTTFT (ms)TPS (tok/s)Target
17804.6≤3000 ms
210614.8≤3000 ms
411644.6≤3000 ms
815344.4≤3000 ms
1621543.9≤3000 ms
3232542.9>3000 ms
6454231.7>3000 ms
128141521.5>3000 ms
160183841.3>3000 ms
176207111.4>3000 ms
192——Failed
Images per requestTTFT (ms)TPS (tok/s)Target
17804.6≤3000 ms
28334.6≤3000 ms
410644.8≤3000 ms
817115.2≤3000 ms
1633645.7>3000 ms
326442217.8>3000 ms
6414952212.3>3000 ms
128353656.7>3000 ms
2561356643.7>3000 ms
512——Failed

Alpamayo2-Super (34.3B parameters), served in BF16 format with vLLM on Jetson AGX Thor, starts answering a single camera that sends one 720p image after 780 ms (time to first token, TTFT), then writes 4.6 tok/s.

With 256 images per camera at 720p, the answer starts after 135,664 ms. With one 2K image, after 838 ms.

At the default target of a mean TTFT within 3,000 ms (720p, one image per camera), it keeps up with 16 cameras at once.