How to Quantize a Large Language Model with GGUF or AWQ

Learn how to quantize large language models using GGUF or AWQ in this 26-minute video tutorial. Explore the reasons for quantization, understand different quantization methods, and compare GGUF, BNB, AWQ, and GPTQ techniques. Follow step-by-step instructions for quantizing models with AWQ and GGUF (GGML), and gain access to advanced fine-tuning resources, including scripts for unsupervised and supervised fine-tuning, dataset preparation, and embedding creation. Discover valuable resources such as presentation slides, GitHub repositories, and related research papers to enhance your understanding of LLM quantization techniques.

Syllabus

How to quantize a large language model
: Why quantize a language model
What is quantization
Which quantization to use?
GGUF vs BNB vs AWQ vs GPTQ
How to quantize with AWQ
How to quantize with GGUF GGML
Recap

Taught by

Trelis Research

Reviews

5.0 rating, based on 1 Class Central review

Start your review of How to Quantize a Large Language Model with GGUF or AWQ

Bandham Manikanta

Good course and the explanation is to the point. For anyone who is looking to understand how AWQ and GGUF quantizations works, this is a good start.

JavaScript Programming for Beginners

35% Off Finance Skills That Get You Hired - Code CFI35

Taught by

Master AI & Data—50% Off Udacity (Code CC50)

Double Inference Speed with AWQ Quantization

Unlocking Local LLMs with Quantization

Quantizing LLMs and Converting to GGUF Format for Faster and Smaller Models

GGUF Quantization of Large Language Models Using LLAMA.cpp

Simple Quantization of LLMs - A Hands-on Guide to Absolute Max and Zero Point Methods

The Most Addictive Python and SQL Courses Ad

From Zero to GenAI: 9 Unique Ways to Understand Large Language Models

Write Prompts That Actually Work: ZTM’s Prompt Engineering Bootcamp Review

25 Resources to Learn Generative Engine Optimization in 2026

12 Best Retrieval-Augmented Generation (RAG) Courses in 2026

14 Best Machine Learning Courses for 2026: Scikit-learn, TensorFlow, and more

Never Stop Learning.