Tech
[Local LLM] 笔记本 125B 模型 Q4 量化， xHigh256k 调优峰值 64tps。附部署和调优源码
笔记本：幻 X2025 windows
96G 显存分配 32G RAM
操作模式：增强模式
修了识图，去拒答
配置：q4xs 量化、上下文 256K ，配置如下，96G 显存分配 32GRAM
峰值 64.63TPS
智商类似不降智 opus4.6
https://github.com/xszwow/Strata
Read the full discussion on V2EX
This article was aggregated from V2EX. Click to join the conversation.
View on V2EX
Related Trends in Tech
111 Blog Posts To Learn About Entertainment
Theo de Raadt: The Man Who Built the Internet's Locks
Bitcoin Is Not Just an Investment. It’s an Escape Hatch From the Financial Gulag
Privacy, Personalization and Precision Health: Interview with DEPH Labs CEO Lisa Loud
How to Make Your Open-Source Library Easier for AI Agents to Find, Trust, Use and Love
Spec-Driven Development: Let the Specification Drive the Code