[KongchangAI]
Unverified50% confidenceBenchmarkExact time

Apple M2/M3 芯片采用统一内存架构(UMA),llama.cpp 通过 Metal API 可达到约 30-50 tokens/秒的 7B 模型推理速度

1
Sources
50%
Confidence
Long-term
Relevance
7/6/2026
First Seen

Sources

Related Claims

Cite This Claim

Stable URI
https://kongchang.com/claim/115925
API
curl https://kongchang.com/api/v1/knowledge/claims/115925
MCP
get_claim(id=115925)