[KongchangAI]
Unverified60% confidenceFactExact time

在4×RTX 3090 SXM4配置下,GLM-5.2量化版本的Token生成速度约为6.3-6.8 tokens/秒,提示评估速度约为10.6 tokens/秒

2
Sources
60%
Confidence
Medium-term (~90 days)
Relevance
7/2/2026
First Seen
Valid until: 9/30/2026

Sources

4000美元4张RTX3090本地运行GLM-5.2全攻略
bilibili程序员-智能译站6/24/2026

Related Claims

Cite This Claim

Stable URI
https://kongchang.com/claim/40845
API
curl https://kongchang.com/api/v1/knowledge/claims/40845
MCP
get_claim(id=40845)