Author

Brian

Staff Technical Writer

2 posts

Brian educates on using software and tools effectively. He is pragmatic in each of his articles and provides value in terms of work that can actually be done today.

$GGUF, GPTQ, AWQ, EXL2 quantization formats compared: how model weights, runtime overhead, and KV cache stack up in memory$

AI & Machine Learning

GGUF, GPTQ, AWQ, EXL2: How LLM Quantization Formats Actually Use Memory

Compare GGUF, GPTQ, AWQ, and EXL2 memory use, from Q4_K_M file size to KV cache growth and runtime overhead.

Brian Jul 2, 2026 12 min read

Unified memory explained: discrete GPU memory requires a copy across PCIe between system RAM and VRAM, while unified memory is one shared pool the CPU and GPU both access directly

AI & Machine Learning

What Is Unified Memory, and Why Does It Let a Mini PC Run a 235B Model?

Unified memory lets a compact AI PC load 235B-class models no single 24-32GB GPU can hold. What it is, why it works, and why bigger doesn't mean faster.

Brian Jul 2, 2026 11 min read