Expired50% confidenceBenchmarkExact time
On a Mac Studio equipped with an M4 chip, Agent A1 achieved a local inference speed of 95 tokens/second.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
7/22/2026
First Seen
This claim has expired. It is kept for the record and no longer describes the current state.
Valid until: 10/20/2026(expired)
Sources
Related Claims
UnverifiedThe Apple M4 Pro's Neural Engine reaches 38 TOPS, the Qualcomm Snapdragon X Elite integrates a 45 TOPS NPU, and Intel Core Ultra has also integrated an NPU to support local AI inference.62% similarVerifiedApple's Neural Engine first appeared with the A11 Bionic chip in 2017, with the A11 capable of executing 600 billion operations per second, while the A18 Pro chip has reached 35 trillion operations per second.61% similarUnverifiedApple M-series chips accelerate AI inference through the Metal Performance Shaders (MPS) framework, but their performance does not match NVIDIA's CUDA ecosystem.61% similarVerifiedThe M4 chip's Neural Engine can perform 38 trillion operations per second (38 TOPS)60% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/593884API
curl https://kongchang.com/api/v1/knowledge/claims/593884MCP
get_claim(id=593884)