Unverified50% confidenceBenchmarkExact time
During an 8,000-token run, Ollama reported a duration of 125 seconds, while the client actually waited 725 seconds, with the difference being gateway queuing time that is invisible to the server-side numbers.
1
Sources
50%
Confidence
Short-term (~14 days)
Relevance
10/5/2026
First Seen
Valid until: 10/19/2026
Sources
Related Entities
Related Claims
UnverifiedIn the long-context archiving experiment, 8 requests each input approximately 261,000+ tokens and each completed approximately 1,022 outputs; the total throughput of the joint decoding window was 214.85 tokens per second, approximately 26.86 per request, but the window was only approximately 2.28 seconds and prefilling was serial or interleaved.75% similarUnverified对于500 Token的回答，流式输出可以让用户在首Token延迟（约500ms）后就开始看到内容，而非等待完整生成（约10秒）73% similarUnverifiedOfficial comparison data shows that for the same ticket booking task, the original BrowserUse had a median time of 9.45 seconds, while jev-ultrafast required only 7.09 seconds.72% similarUnverified在传统SSR架构下，即便服务器响应时间控制在100ms以内，用户实际感知的延迟往往在300-800ms之间70% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/977214API
curl https://kongchang.com/api/v1/knowledge/claims/977214MCP
get_claim(id=977214)