📚 Blogs

A Linux laptop running a local llama.cpp server with an NVIDIA GPU setup.

Running local LLM models with llama.cpp

Build llama.cpp with CUDA support, run GGUF models through llama-server, and tune common flags for fitting larger or MoE models on an 8GB RTX 4060 laptop GPU.

Arch Linux Dual Boot Installation

How I installed Arch Linux as a dual boot setup with Windows 11, from partitioning and pacstrap to GRUB, KDE Plasma, and laptop-specific NVIDIA brightness fixes.

Running DeepSeek Locally + Utilizing Your GPU

Learn how to run DeepSeek AI models on your local machine using GGUF files and Python, with full GPU utilization and custom configuration options.

Nginx Configuration

Learn how to set up Nginx as reverse proxy on AWS EC2 instances with practical configuration examples and SSL setup tips.