4-bit Quantization을 통한 T4 GPU 기반의 Meeting Minutes AI 파이프라인 구현
Build a Meeting Minutes AI From Raw Audio
일 3,000건 기준 Claude API 대비 Llama 자가 호스팅 비용 최적화
Is Claude API Worth $3/1M Tokens Over Self-Hosted Llama?
AWS Cloud9 기반 LLaMA 3.2 Self-Hosted AI Task Manager 구현
I Built an AI Task Manager on AWS Cloud9 with OpenClaw and LLaMA 3.2 — Fully Self-Hosted
Groq API와 Llama 3.2 기반 저지연 Local AI Agent 구현
Voice-to-Action: A Local AI Agent with Llama 3.2 and Groq
Llama 3.2 1B 기반의 Low-Footprint 로컬 Voice AI Agent 설계
From Voice to Code: Architecting a Local AI Agent with Llama 3.2 & Streamlit