cpp（⽤于合并分⽚⽂件） /bin/bash -c "$(curl -fsSL https://raw.githubusercontent.com/Homebrew/install/HEAD/install.sh)" brew install llama.cpp 2. 下载并合并模型分⽚： 3. 安装Ollama： 4. 创建Modelfile： 5. 运⾏模型： 4. 性能调优与测试 GPU利⽤率低：升级⾼带宽内存（如DDR5 DeepSeek-R1-UD-IQ1_M-00001-of-00004.gguf DeepSeek-R1-UD-IQ1_S.gguf curl -fsSL https://ollama.com/install.sh | sh FROM /path/to/DeepSeek-R1-UD-IQ1_M.gguf PARAMETER num_gpu 28 # 每块RTX 4090加载7层（共4卡） PARAMETER eek/DeepSeek- R1/playground  11. POE：https://poe.com/DeepSeek-R1  12. Cursor：https://cursor.sh/  13. Monica：https://monica.im/invitation?c=ACZ7WJJ9  14. Lambda：https://lambdalabs.com/ 

```bash ``` text wrapper), and paste it in a new file called: “rename_files.sh”. 2. Open a terminal window and type: . rename_files.sh. It will ask to enter a folder name, e.g. test. and hit enter. 3. The

compiled TVM to the SDCard Step 7: Install kernel module cma.ko and run apps/vta_rpc/start_rpc_server.sh Step 8: Configure vta/config/de10nano_config.json to vta_config.json Step 9: Go to vta/hardware/intel