[KongchangAI]
Verified90% confidenceFactTime unknown

一个70B参数的FP16模型大约需要140GB显存,INT8量化后约需70GB,INT4量化后约需35-40GB

46
Sources
90%
Confidence
Long-term
Relevance
6/1/2026
First Seen

Sources

Related Entities

Cite This Claim

Stable URI
https://kongchang.com/claim/21173
API
curl https://kongchang.com/api/v1/knowledge/claims/21173
MCP
get_claim(id=21173)