VLM Inference Benchmark Explorer

Cosmos-Reason1-7B on Jetson Orin NX 16GB — Q4_K_M, llama.cpp vision-language inference benchmark

Open this configuration in the VLM Inference Benchmark Explorer

ModelCosmos-Reason1-7B
Parameters8.3B
DeviceJetson Orin NX 16GB
QuantizationQ4_K_M
Image size720p
Images per camera1
Max Cameras (TTFT ≤ 3000 ms)>3000 ms
Enginellama.cpp
CamerasTTFT (ms)TPS (tok/s)Target
1768112.0>3000 ms
2113749.3>3000 ms
4243399.2>3000 ms
Images per requestTTFT (ms)TPS (tok/s)Target
1768112.0>3000 ms
32273012.1>3000 ms
53775511.7>3000 ms

Cosmos-Reason1-7B (8.3B parameters), served in Q4_K_M format with llama.cpp on Jetson Orin NX 16GB, starts answering a single camera that sends one 720p image after 7,681 ms (time to first token, TTFT), then writes 12 tok/s.

With 5 images per camera at 720p, the answer starts after 37,755 ms. With one 1080p image, after 23,305 ms.

At the default target of a mean TTFT within 3,000 ms (720p, one image per camera), not even one camera is answered in time.