CX
Home
Search
Archive
CX
Article
7
Category
1
Tags
1
Archive
Search
Category
Tags
Lazy loaded image
WSL2 + RTX 4060 Ti 16GB + llama.cpp 部署 Qwen3.8-27B-GGUF 量化
Post on: 2026-8-23
Last edited: 2026-9-3
Views
Catalog
0%
一、安装基础编译环境二、安装 WSL 专用 CUDA Toolkit三、编译上游 llama.cpp四、根据显存选择模型五、下载模型六、运行模型
CX
CX
Attention Is All You Need
Article
7
Category
1
Tags
1
Latest posts
WSL2 + RTX 4060 Ti 16GB + llama.cpp 部署 Qwen3.8-27B-GGUF 量化
WSL2 + RTX 4060 Ti 16GB + llama.cpp 部署 Qwen3.8-27B-GGUF 量化
2026-9-3
Cambridge Dictionary 2 API
Cambridge Dictionary 2 API
2025-3-15
新vps到手后我会做的几件事
新vps到手后我会做的几件事
2025-3-15
AFFINE selfhost
AFFINE selfhost
2025-2-21
Wills’Mineral Processing Technology Learning Log
Wills’Mineral Processing Technology Learning Log
2024-9-24
Next.js Learning Notes
Next.js Learning Notes
2024-9-24
Announcement
MillCloud is under development@CX
 
Catalog
0%
一、安装基础编译环境二、安装 WSL 专用 CUDA Toolkit三、编译上游 llama.cpp四、根据显存选择模型五、下载模型六、运行模型
2024-2026CX.

CX | Attention Is All You Need

Powered byNotionNext 4.10.10.