CCrimsunDevinnathan-language-processing.hashnode.dev·Oct 28, 2025 · 4 min read🧠Running DeepSeek-OCR Locally with FlashAttention2 on RTX 3080 (No A100 Needed)“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...00
CCrimsunDevinnathan-language-processing.hashnode.dev·Apr 19, 2025 · 4 min readThe Tools and Plugins I Use to Build Local AI Projects (Without Spending a Fortune)Hi! I’m a full-stack software engineer building AI tools on the side using just my gaming PC, a 3080, and an obsession with doing things the hard way. Most of my projects are powered by open models and local-first frameworks—no fancy clusters or clou...00
