6 min read
Running LLMs Locally: Lessons in Quantization and Ollama Optimization
An in-depth technical analysis of CPU-bound quantization performance, evaluating Q4_K_M vs Q8_0 GGUF inference latency on host RAM.
Local AIOllamaPython
Read Article →Markdown-driven engineering notebook parsed dynamically with YAML frontmatter metadata.
An in-depth technical analysis of CPU-bound quantization performance, evaluating Q4_K_M vs Q8_0 GGUF inference latency on host RAM.
Debugging hardware sensor jitter during my robotics internship using C++ complementary filters to combine accelerometer and gyroscope data.
Architecting Row-Level Security (RLS) policies in PostgreSQL to enforce strict data isolation across college lab departments.
Configuring a minimal Linux development environment with zsh, Kitty, Neovim, and Ollama background process management.