Unverified50% confidenceFactExact time
On a shared server with a Xeon E5-2450 v2, 15GB RAM, and Debian 13, the measured BGE-M3 cold load took 2.66 seconds against an old timeout of 2.50 seconds; the per-turn limit was adjusted to 2.8 seconds and embedding batching to 60 seconds.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/18/2026
First Seen
Valid until: 1/16/2027
Sources
Related Entities
Related Claims
UnverifiedBEINGS的冷启动加载时间分别为7.5秒（SmolLM2 273MB）、13.4秒（Qwen 483MB）、26.8秒（Llama 1238MB），缓存后降至1.0、2.2、3.1秒。77% similarUnverifiedOn the test machine (Intel i5-13420H, 16 GB RAM, no discrete GPU), Laya-Heart's card median latency was 0.44 seconds, the first full reply 3.6 seconds, and two replies 5.8 seconds; on an idle machine these were 0.39 seconds, 3.5 seconds and 5.0 seconds respectively.72% similarUnverifiedLaya's load time has been reduced from approximately 17 seconds to around 9 seconds, and peak host memory requirements have been halved.72% similarVerifiedAfter switching to Plan B, scene loading time was reduced from 3.3 seconds to approximately 0.5 seconds, approximately 6.8 times faster.71% similarVerifiedA 3-billion-parameter Llama takes 1 to 3 seconds per call on CPU, while a 70B model takes 40 seconds per call.71% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1062257API
curl https://kongchang.com/api/v1/knowledge/claims/1062257MCP
get_claim(id=1062257)