Unverified50% confidenceBenchmarkExact time
For a cold-start 27k-token fresh session, the original llama.cpp required 245 seconds, the author's fork took 228 seconds on Mac alone, and was reduced to 168 seconds after connecting the phone.
1
Sources
50%
Confidence
Long-term
Relevance
10/2/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedWhen Tidy processes short text (100–500 tokens), inference latency is approximately 1–2 seconds for initial loading plus 200–800 milliseconds of computation, with continuous use impacting battery life by less than 5% per hour.70% similarUnverifiedreMarkable书写延迟通常低于21毫秒69% similarUnverified电话场景端到端延迟低于800毫秒感觉流畅，超过2秒用户会明显感知停顿，超过3秒会误以为通话中断69% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/968229API
curl https://kongchang.com/api/v1/knowledge/claims/968229MCP
get_claim(id=968229)