Ternary-Bonsai-27B-Q2_0.gguf 模型本地部署
1.下载源码git clone https://github.com/PrismML-Eng/llama.cpp2编译cd llama.cpp# Build with CUDA support
cmake -B build -DGGML_CUDAON && cmake --build build -j3.启动服务./bin/llama-server -m /mnt/87b26cb3-9627-446a-b048-2f61a945fafa/Ternary-Bonsa…
2026/8/7 10:02:15