The Math That Shrinks ChatGPT Onto a Laptop
How does a 326GB language model become something you can run locally on a laptop? In this Nerdy Dives episode, we break down the engineering behind local LLMs: quantization, memory bandwidth, GGUF, llama.cpp, GPTQ, AWQ, QLoRA, and why your GPU is often waiting on memory instead of doing math. This is the real story behind “AI on your laptop” — not hype, but the papers, numbers, and systems tricks that made it possible. We cover: • Why LLM inference is usually memory-bound, not compute-bound • How FP16 weights turn 70B models into 140GB monsters • Why naive quantization breaks at scale • The 0.1% outlier features that can destroy a model if handled wrong • How LLM.int8(), GPTQ, and AWQ made 8-bit and 4-bit models practical • Why GGUF and llama.cpp became the foundation of local AI • How QLoRA made finetuning huge models possible on one GPU • Why MoE and distillation shrink the work even further If you’ve used Ollama, LM Studio, llama.cpp, GGUF models, or local AI tools and wondered how this stuff actually works, this is the deep dive. Sources include: LLM.int8(), GPTQ, AWQ, QLoRA, llama.cpp, GGUF docs, OpenAI gpt-oss, and knowledge distillation papers. Nothing in this video is sponsored. All models shown were run locally.

How do Graphics Cards Work? Exploring GPU Architecture

But what is quantum computing? (Grover's Algorithm)

LLM Eval with Real Numbers: Kappa, F1, pass^k, ASR Curves, Paired Tests

Paper Dives: MapReduce Is Back - And It Fixes Broken LLM Pipelines | DocETL

AI Agents for Beginners – Part 1 (Free Labs)

Sodium Ion Batteries Will be 80% Cheaper & Last LONGER!

This Battery Lasts for 30 Years And China Just Put It on the Grid

Paper Dives: Verbalizable Representations Form a Global Workspace in Language Models

Anthropic’s Fable 5 Was Banned for 19 Days. Here’s the Timeline

The Scariest Chart In Electrical Engineering

Zig 2026: No-AI Policy, $670K Foundation, Left GitHub & Why Zig Isn’t 1.0 - Andrew Kelley Explains

The World's Most Important Machine

Everything That Actually Matters for Local AI

He Risked Everything To Warn You: No One Is Ready For What's Coming, And The AI Companies Know It!

System Design Explained: APIs, Databases, Caching, CDNs, Load Balancing & Production Infra

HOW WIFI ACTUALLY WORKS

Local AI Explained | Hardware, Setup and Models

Andrej Karpathy: From Vibe Coding to Agentic Engineering w/ Stephanie Zhan

NVIDIA CEO Jensen Huang's Vision for the Future

