Expired50% confidenceBenchmarkExact time
This approach achieves a real-time running speed of 25 frames per second (FPS) on an NVIDIA Jetson ORIN.
1
Sources
50%
Confidence
Short-term (~14 days)
Relevance
10/14/2026
First Seen
This claim has expired. It is kept for the record and no longer describes the current state.
Valid until: 10/28/2026(expired)
Sources
Related Entities
Related Claims
UnverifiedThe Jetson Orin AGX can simultaneously decode 32 channels of 1080P video streams and perform real-time AI inference, with power consumption controlled within the 15~60W range.75% similarUnverifiedThe project uses TensorRT FP16 quantization and an input resolution of 512×512, with a current frame rate of 20–30 FPS.70% similarUnverifiedCloud-based APIs can typically achieve output speeds of tens to hundreds of tokens per second, while consumer-grade GPUs running 27B models often only reach 10–30 tokens per second.69% similarUnverifiedThe typical generation speed of an NVIDIA RTX 4090 running a similarly scaled Q4 quantized model is in the range of 40–60 TPS69% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1024108API
curl https://kongchang.com/api/v1/knowledge/claims/1024108MCP
get_claim(id=1024108)