Gptq | martinuke0's Blog

Int4-quantized language model on a laptop

Hands-On Int4 Quantization Portfolio: Build a GPTQ/AWQ-Powered LLM CV Project

Learn how to quantize a language model to int4, integrate GPTQ and AWQ, and ship a runnable CV project that impresses hiring managers.

GPTQ quantization engine pipeline diagram

Building a GPTQ Weight Quantization Engine from Scratch: Fisher Scoring & Mixed-Precision Calibration

Learn to build a functional GPTQ quantization engine from scratch, complete with Fisher information scoring and mixed-precision calibration, and how to signal systems-level engineering skill to hiring managers.

A visual representation of a neural network weight matrix being compressed into INT4 format.

From Scratch: Building a GPTQ INT4 Quantizer in Pure Python

Learn how to build a GPTQ INT4 quantizer from scratch in pure Python, demonstrating deep systems and ML engineering skills that stand out to hiring managers.

Abstract visualization of a 4-bit quantized weight matrix being dequantized into activations for a matrix multiplication.

Build a GPTQ-Style Int4 Quantization Engine From Scratch

Build a real int4 quantization engine from scratch: grouped scales, zero points, and a fast dequant matmul kernel that runs without CUDA. A substantive portfolio project that signals real systems skill.

Layered diagram of a quantization pipeline showing calibration, packing, and fused dequantize-matmul.

Build a GPTQ int4 Quantization Engine in Python/NumPy

Ship a runnable int4 weight-only quantization engine from scratch: GPTQ-style calibration, group-wise affine scales, and a fused dequantize-matmul kernel. Built to demonstrate real ML systems skill on a portfolio.