mattpetters

Self-Hosted Qwen3.6-27B on RunPod + OpenAI Codex CLI

End-to-end guide for running Qwen3.6-27B as a private, self-hosted coding agent accessible from your Mac via SSH tunnel and OpenAI Codex CLI. Hardware-tested on RTX PRO 6000 Blackwell. ~$1.91/hr.

Prerequisites

• RunPod account with credit loaded
• SSH key on your Mac (~/.ssh/id_ed25519 and .pub)
• Node.js 18+ on your Mac (for Codex CLI)
• Hugging Face account + read token (avoids rate limits on downloads)

mattpetters

​

https://ziglang.org/documentation/master/#Pointers Local std lib docs:

$ zig std

Browse the std lib code

$ vi $(zig env | jq -r .std_dir)

mattpetters

$ wget http://downloads.sourceforge.net/project/glfw/glfw/3.0.1/glfw-3.0.1.zip
$ unzip glfw-3.0.1.zip
$ cd glfw-3.0.1/
$ mkdir build
$ cd build
$ export MACOSX_DEPLOYMENT_TARGET=10.8 
$ cmake -D GLFW_NATIVE_API=1 -D CMAKE_OSX_ARCHITECTURES="i386;x86_64" -D BUILD_SHARED_LIBS=ON -D CMAKE_C_COMPILER=clang ../
$ make
$ ls -l src/libglfw*

mattpetters

Software Engineering Reading

adapted from an original list by Jay Baxter

https://www.amazon.com/gp/richpub/listmania/fullview/R2LC80THGVDJHI/ref=cm_lm_byauthor_title_full

https://www.amazon.com/gp/richpub/listmania/fullview/R1C0VA4J8ZBURC/ref=cm_lm_byauthor_title_full

https://www.amazon.com/gp/richpub/listmania/fullview/R2FZ98PSM92N7F/ref=cm_lm_byauthor_title_full

Associate developer