No Cloud, No Problem: AI on Your Own Terms | Adrian Boguszewski | LLMday Warsaw 2026 Q1 скачать в хорошем качестве

No Cloud, No Problem: AI on Your Own Terms | Adrian Boguszewski | LLMday Warsaw 2026 Q1

LLMday Warsaw 2026 Q1 - February 12 Grab your ticket for the next LLMday: https://www.llmday.com Upcoming LLMday CFPs: https://cfp.ninja/?q=llmday&status=op... Chapters 00:00 Intro: You Don’t Need the Cloud for LLMs 00:25 The Deployment Challenge: Cloud vs Local Tradeoffs 01:48 Live Demo Setup: Running Qwen 3 8B on Localhost 02:32 Proof It’s Local: Integrated GPU Inference & Performance 04:25 Switching Devices: Same Model on the NPU 05:18 Tokens/sec & Power Draw: NPU vs GPU vs CPU Explained 07:31 Back to Slides: Hardware Requirements (CPU/GPU/NPU + Memory) 09:18 Serving Locally with OpenVINO Model Server (OVMS) 10:42 OpenVINO & GenAI Pipelines: Frameworks, Devices, Use Cases 12:37 Models & Code: Hugging Face, Optimum, and 3-Line Pipelines 14:37 Quantization 101: Weight Compression (INT8/INT4) with NNCF 18:31 Quality vs Size: Perplexity, RAM Savings, and Why It Matters 20:10 Wrap-Up, GitHub Demo Link, and Audience Q&A