---
title: "Discussion on \"Quantization, Explained: From FP32 to INT4, and What Each Precision Costs You\" | Hashnode"
description: "Discussion on \"Quantization, Explained: From FP32 to INT4, and What Each Precision Costs You\". In LoRA & DoRA and our other posts on large models, we keep running into the same wall: memory. This post is about the number formats behind that wall.\nWhen you run a modern language model, memory is"
url: "https://hashnode.com/posts/quantization-explained-from-fp32-to-int4-and-what-each-precision-costs-you/6aed0294c8a8a0842336cfe1"
---

[Feed](https://hashnode.com/feed) /

Discussion

# [Quantization, Explained: From FP32 to INT4, and What Each Precision Costs You](https://gfactor.hashnode.dev/quantization-explained-from-fp32-to-int4-and-what-each-precision-costs-you?utm_source=hashnode&utm_medium=feed)

In LoRA & DoRA and our other posts on large models, we keep running into the same wall: memory. This post is about the number formats behind that wall. When you run a modern language model, memory is

6d ago · 14 min read · gfactor.hashnode.dev  
Read the article

-   [#quantization](https://hashnode.com/tag/quantization)
-   [#machine-learning](https://hashnode.com/tag/machine-learning)

## Written by

[Aleksei Romanov](https://hashnode.com/@gfactor)

@gfactor · United States

  
[View profile](https://hashnode.com/@gfactor)

Ex-Apple GenAI engineer, building an LLM post-training platform at g factor technologies

Ex-Apple GenAI engineer, building an LLM post-training platform at g factor technologies

## Responses

Markdown supported · ⌘↵ to post

No responses yet.