[KongchangAI]
Verified70% confidenceBenchmarkExact time

在RTX 5070(12GB显存)配置下,本地Qwen3 9B模型的输出速度达到约70-76 token/秒

4
Sources
70%
Confidence
Medium-term (~90 days)
Relevance
8/25/2026
First Seen
Valid until: 11/23/2026

Sources

Related Entities

Related Claims

Cite This Claim

Stable URI
https://kongchang.com/claim/798209
API
curl https://kongchang.com/api/v1/knowledge/claims/798209
MCP
get_claim(id=798209)