# Quantization in Depth: From INT4 to FP8 — Shrinking Your Model 4×, Speeding 2×

> Source: https://sukruyusufkaya.com/en/learn/llm-muhendisligi/quantization-derinlemesine-int4-fp8
> Updated: 2026-05-13T13:00:30.375Z
> Category: LLM Mühendisliği
> Module: Module 16: Production Engineering — Self-Host, Quantization, Serving, Monitoring
**TLDR:** Mathematical and engineering anatomy of LLM quantization: INT8, INT4, FP8 formats, GPTQ (Frantar 2022) vs AWQ (Lin 2023) vs GGUF (Gerganov) algorithms, quality-size-speed trade-offs. Quantizing Llama-3-8B Turkish DPO model with 4-bit AWQ, measuring quality loss, running Llama-3-70B on RTX 4090, mobile device deployment.