Portfolio

Owning Your Agent Part 2 — private WHOOP agent with Hermes and Qwen on dual RTX 3090s
  • Hermes
  • Dual GPU
  • Agent

Owning Your Agent Part 2 — Local WHOOP Agent with Hermes and Qwen on Dual RTX 3090s
Go Big or Go Home, Part 3 — multi-model inference benchmarking with vLLM, llama.cpp, and agentic workflows
  • vLLM
  • llama.cpp
  • Benchmarks

Go Big or Go Home, Part 3 — The Inference Lab: Multi-Model Benchmarking with vLLM, llama.cpp, and Agentic Workflows
Go Big or Go Home, Part 2 — commissioning and validating the new Threadripper PRO AI cluster
  • Commissioning
  • Hardware
  • Validation

Go Big or Go Home, Part 2 — Commissioning the New Threadripper PRO AI Cluster
Go Big or Go Home, Part 1 — dual RTX 3090 Threadripper PRO AI cluster with 128 GB ECC memory
  • Local AI
  • Threadripper
  • Multi-GPU

Go Big or Go Home, Part 1 — Dual RTX 3090 Threadripper PRO AI Cluster
Owning Your Agent Part 1 — local agent stack with Hermes Agent + Qwen3.5-27B + GLM-4.7-Flash on dual RTX 3090s
  • Hermes
  • Local AI
  • Agent

Owning Your Agent Part 1 — Local Agent with Hermes on Dual RTX 3090s
Dual RTX 3090 local LLM infrastructure build with 48 GB VRAM
  • Infrastructure
  • CUDA
  • LLM

Local LLM Infrastructure — Dual RTX 3090 Cluster, 48 GB VRAM
Melange — Apple Silicon LLM memory profiler and KV cache analyzer built in Rust
  • Rust
  • Apple Silicon
  • LLM

Melange — Apple Silicon LLM Memory Profiler & KV Cache Analyzer (Rust)
Personal portfolio website project — HTML, CSS, and JavaScript built by Zachary Cangemi
  • HTML
  • CSS
  • JS

Personal Portfolio Website