Unverified50% confidenceFactExact time
The NVIDIA Jetson series covers an AI compute range of 10–275 TOPS, the Google Coral TPU provides 4 TOPS of INT8 inference capability at only 2W power consumption, and the latest version of the Apple Neural Engine can reach 35 TOPS.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
8/18/2026
First Seen
Valid until: 11/16/2026
Sources
AI实时格斗计分系统：骨骼追踪网络延迟问题与优化方案
Related Claims
UnverifiedThe NVIDIA Jetson AGX Orin delivers approximately 275 TOPS of INT8 inference performance, with a sustained full-load power consumption of up to 60 W.73% similarUnverifiedJetson Xavier NX是NVIDIA推出的嵌入式AI计算模块，搭载384个CUDA核心的Volta架构GPU和6核Carmel ARM处理器，提供最高21 TOPS的AI算力72% similarVerifiedThe Apple M4 chip's Neural Engine delivers 38 TOPS, Qualcomm's Snapdragon 8 Elite Hexagon NPU reaches 45 TOPS, and the NPU integrated in Intel's Lunar Lake delivers 48 TOPS.71% similarUnverifiedThe Jetson AGX Orin features a 12-core ARM Cortex-A78AE CPU and a 2048-core Ampere architecture GPU, providing up to 275 TOPS of AI compute performance.70% similarUnverifiedThe NVIDIA RTX 4090 delivers 1321 TOPS INT8 inference performance.70% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/765158API
curl https://kongchang.com/api/v1/knowledge/claims/765158MCP
get_claim(id=765158)