Unverified50% confidenceBenchmarkExact time
BM25 can complete full retrieval of tens of thousands to hundreds of thousands of documents at the millisecond level on a single machine, with no need for GPU or embedding model support whatsoever.
1
Sources
50%
Confidence
Long-term
Relevance
9/3/2026
First Seen
Sources
Related Entities
Related Claims
Unverified巨型模型存储全部权重需数TB显存，运行需要由A100或H100组成的GPU集群69% similarUnverifiedA single inference at the million-token level requires tens to hundreds of gigabytes of high-end GPU memory (A100/H100 class).65% similarUnverifiedFor small teams with a few professional-grade GPUs (such as A100 80GB or H100), a 270GB model has entered the range of operability.65% similarUnverifiedFor 1 million tokens, the KV Cache alone can consume hundreds of GB of VRAM at FP16 precision, far exceeding the 80 GB capacity limit of a single A100/H100.64% similarUnverifiedH100的内存带宽约3.35TB/s，GPT-4规模模型单次生成一个Token需读取约1TB参数数据，理论上每秒最多生成约3个Token64% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/847337API
curl https://kongchang.com/api/v1/knowledge/claims/847337MCP
get_claim(id=847337)