Unverified50% confidenceBenchmarkExact time
BTTF experiments show: the untrimmed database occupies 1420 MB with queries taking about 410.5 milliseconds; after filtering out clocks and signals with no toggles, the size drops to 395 MB and the time drops to 94.8 milliseconds; if signals with toggle rates below the average are further removed, the database can shrink to 185 MB, but activity coverage is only 64.23%.
1
Sources
50%
Confidence
Long-term
Relevance
10/19/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedAt a scale of 1 million vectors, PRISM achieves 99% recall and 15 milliseconds median latency on a 2GB c8g.medium; HNSW on a 4GB c8g.large is 392 milliseconds, with building taking about 21.7 hours and exhibiting memory thrashing.70% similarUnverifiedIf the quantized model weights are 150 GB, reading the weights once at a bandwidth of 273 GB/s takes approximately 0.55 seconds, giving a theoretical single-token generation speed of approximately 1.8 tokens/s (excluding computation latency and cross-node communication overhead).70% similarUnverified纯内存操作的延迟通常比向量数据库方案低1-2个数量级，Redis等内存数据库的P99延迟可控制在1ms以内，而远程向量检索往往需要10-100ms69% similarUnverified传统数据库即使是内存数据库，通常也需要微秒级别的查询时间，Redis等方案仍需经过网络栈（约50-200微秒）68% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1067554API
curl https://kongchang.com/api/v1/knowledge/claims/1067554MCP
get_claim(id=1067554)