Expired50% confidenceFactTime unknown
With the global virtual repository enabled in Bun v1.3.14, warm install time drops from 841 ms to 115 ms on macOS with approximately 1,400 packages, a 7.3× speedup.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
7/2/2026
First Seen
Valid until: 9/30/2026(expired)
Sources
Related Claims
Unverified一个800万参数（8.3M）的沙盒引擎在2019年发布的6核桌面CPU上跑出约2000 tokens/秒的解码速度65% similarUnverifiedIn a controlled test, the 35B model ran at approximately 100 tokens/second (Mac Studio), roughly five times the 9B model's 16 tokens/second63% similarUnverifiedSmall models (1B–7B parameters) used for text completion tasks can run smoothly on Macs with 8 GB or more of unified memory, with inference latency kept within a few hundred milliseconds.62% similarUnverified基于MLX框架，顶配Mac机型运行Llama-3-70B量化模型可达约20 tokens/秒的生成速度60% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/55599API
curl https://kongchang.com/api/v1/knowledge/claims/55599MCP
get_claim(id=55599)