Tuan Pham
SYS // OK
MENU

Tuan Pham — Director of Software Engineering

00 // About this place

Welcome to my corner of the web, a place for the things I build, the ideas I’m exploring, the lessons I’ve learned, the curiosities I keep chasing, and the art of making complex things work.

Value loaded // ready
tpham@ubuntu: ~/portfoliobash
01 / Writing

Log Records

Architecture notes, leadership thinking, and things I learned the hard way.

3 / 12 records
LOG-001LIVE

Dense vs. MoE Models Explained

A 30B model with 3B active parameters still needs room for its full weights. Here is how dense and mixture-of-experts models differ and what total parameters, routing, memory, and compute mean for local AI.

Tag
/llm /local-ai
Date
Read
10 min read
LOG-002LIVE

Prefill vs. Decode

Tokens per second is not one measurement. Prefill is the work of reading the prompt; decode is the work of generating output. Understanding both explains TTFT, output speed, bandwidth, compute, context length, and benchmark results.

Tag
local-ai
Date
Read
9 min read
LOG-003LIVE

AI Model Files Explained

A base model, an instruct fine-tune, a LoRA adapter, a Safetensors checkpoint, and a GGUF file describe different layers of the AI model stack. Here is how they fit together and which one to download.

Tag
/local-ai
Date
Read
21 min read
Explore all 12 writing records →
02 / Lab

Lab Records

Things I build, break, and benchmark outside of work. Ongoing experimentation, not a polished portfolio.

3 / 11 records
LAB-001ACTIVE

LLM Inference Capacity Planner

An interactive capacity-planning tool for local LLM inference. It estimates model weight storage, KV cache growth, runtime VRAM, minimum host memory, and GPU count from model size, quantization, context length, cache precision, batch size, and the target memory architecture. The breakdown makes the assumptions visible so a hardware plan can be adjusted before downloading a model or buying a GPU.

Stack
Next.js, TypeScript, LLM memory modeling
Date
2026-10-04
Source
Interactive lab tool
Launch tool
LAB-002ACTIVE

Cocktail Bar Machine

An automated cocktail-mixing machine built with nine 12V pumps, supporting up to ten liquors and mixers through a custom PCB, 2020 aluminum extrusion frame, and 3D-printed enclosure. A companion web app can discover and connect to the machine over Wi-Fi, manage ingredients, and prepare hundreds of cocktails with flexible recipe modifications and customization. The project brings together accurate dispensing, pump control, plumbing, wireless connectivity, and a software-driven recipe system in one programmable bar platform.

Stack
2020 extrusion, Wi-Fi, Web app
Date
2026-02-10
Source
github/TPham92/tk-bar
LAB-003SHIPPED

My First Custom PCB

My first custom printed circuit board, designed to control nine pumps for my cocktail bar machine. I designed the schematic and sent the board design to a manufacturer in China for fabrication, then worked through assembly, soldering, and board bring-up. It is a practical lesson in footprints, connector orientation, power routing, and leaving room for test points. The goal is a board I can assemble, measure, and revise without guessing.

Stack
PCB CAD, nine-pump control, soldering
Date
2025-12-04
Source
Personal hardware build
Explore all 11 lab records →
03 / Uses

Systems I build with

Three purpose-built systems, backed by a compact lab and local AI stack.

Full manifest →
SYS-01Primary workstation

Primary workstation

CPU
Intel Core i9-14900K
Memory
64 GB RAM - 6400MT/s
SYS-02Gaming system

Gaming Rig

CPU
AMD Ryzen 7 9800X3D
Memory
96 GB DDR5 RAM - 6400MT/s
SYS-03AI coding system

AI Agentic Engineering Node

System
Mac Studio
Chip
Apple M5 Ultra
Homelab12 nodes // 6 systems
AI runtimellama.cpp / Open WebUI / vLLM