---
title: "CrimsunDev (@crimsunchin) | Hashnode"
description: "CrimsunDev (@crimsunchin) writes on Hashnode. Read their latest articles and follow their work."
url: "https://hashnode.com/@crimsunchin"
---

@crimsunchin

# CrimsunDev

@crimsunchin · Joined April 2025

### [🧠 Running DeepSeek-OCR Locally with FlashAttention2 on RTX 3080 (No A100 Needed)](https://nathan-language-processing.hashnode.dev/running-deepseek-ocr-locally-with-flashattention2-on-rtx-3080-no-a100-needed?utm_source=hashnode&utm_medium=feed)

“You don’t need an A100 to run modern multimodal models — you just need persistence, BF16, and a bit of debugging.” 🚀 Why I Tried This Most multimodal or OCR models assume you’re using a cloud A100 or H100 GPU.But for developers like me running lo...

4 min read · [nathan-language-processing.hashnode.dev](https://nathan-language-processing.hashnode.dev/running-deepseek-ocr-locally-with-flashattention2-on-rtx-3080-no-a100-needed?utm_source=hashnode&utm_medium=feed)

[Oct 28, 2025](https://hashnode.com/posts/running-deepseek-ocr-locally-with-flashattention2-on-rtx-3080-no-a100-needed/6900c0c0f2859c70dd3b658a)

### [The Tools and Plugins I Use to Build Local AI Projects (Without Spending a Fortune)](https://nathan-language-processing.hashnode.dev/the-tools-and-plugins-i-use-to-build-local-ai-projects-without-spending-a-fortune?utm_source=hashnode&utm_medium=feed)

AKA: What I use to build AI tools on my gaming PC—without going broke or waiting on cloud credits

4 min read · [nathan-language-processing.hashnode.dev](https://nathan-language-processing.hashnode.dev/the-tools-and-plugins-i-use-to-build-local-ai-projects-without-spending-a-fortune?utm_source=hashnode&utm_medium=feed)

[Apr 19, 2025](https://hashnode.com/posts/the-tools-and-plugins-i-use-to-build-local-ai-projects-without-spending-a-fortune/6803c1ee7d14128271824fb3)