Local AI: Run Open Models on Your Own Machine [10/2026, ENG]

Обучающие видео » Компьютерные видеоуроки и обучающие интерактивные DVD » Machine/Deep Learning, Neural Networks

Local AI: Run Open Models on Your Own Machine

Год выпуска: 10/2026
Производитель: Udemy
Сайт производителя: https://www.udemy.com/course/local-ai-run-open-models-on-your-own-machine-m/
Автор: Dr. Amar Massoud
Продолжительность: 3h 24m
Тип раздаваемого материала: Видеоурок
Язык: Английский
Описание: This course demystifies local AI for people who have used ChatGPT and Claude but find terms like Hugging Face, Ollama, LM Studio, GGUF, and quantization to sound like a developer-only world. It teaches that local AI is really four pieces, and once you can see them, the field becomes a set of decisions you are equipped to make. By the end, you will have an open model running on your own laptop, doing real work on your own private files with the network switched off—not a demo, but a workflow that reads a folder and writes a document somebody can actually use. What makes the course different is that nothing is faked: every lab is built from a genuine captured session on a real machine, with real pages, application windows, and unedited command output. When a model gets something wrong, that stays in, because what you do next is the actual skill. In Section 6, you watch a real evaluation where a small model catches every planted problem but raises sixteen false alarms, then a prompt fix eliminates the false alarms and destroys the catch rate, then the model that finally worked turns out to be the one nobody expected—something you cannot learn from a scripted success.

You will be able to run an open model entirely on your own machine with no API key, subscription, or data leaving; read a model card and know in two minutes whether it will run on your hardware; choose parameter count, quantization level, and file format on purpose instead of by copying; turn your laptop into a local AI server your own scripts and tools can call; build a workflow that turns a folder of private files into a usable artifact; judge local against cloud with a real evaluation and design the hybrid between them; and apply a five-signal filter that finds workflows where running locally makes the product better. Every tool used is free, 8 GB of RAM is enough to follow along while 16 GB is comfortable, and no coding background is required. The course contains the use of artificial intelligence.
[spoiler="Содержание"]
1 - Why Local AI
1. What You'll Build, And What Local AI Means (04:43)
2. Local Or Cloud — Where Should Intelligence Live (06:31)
3. The Better Question Is It Good Enough For The Job (05:11)
4. The Four Pieces (06:13)

2 - The Vocabulary Decoder
5. Parameters And Model Size — And What The 'E' Means (05:00)
6. Tokens And The Context Window (05:22)
7. Quantization Without The Maths (05:13)
8. File Formats GGUF, safetensors, MLX, LiteRT-LM (04:56)
9. Lab Reading A Model Card Slowly (04:50)

3 - The Open Model Landscape
10. Lab Hugging Face, The Model Warehouse (04:54)
11. The Gemma Family And How To Pick A Size (06:01)
12. The Specialized Gemmas (05:20)
13. Llama, Qwen, DeepSeek, GLM, Mistral, Phi (05:28)
14. Licences, Procurement, And Open Weights vs Hosted (05:23)

4 - Three Ways to Run a Model
15. The Hardware Cheat Sheet (05:40)
16. Lab LM Studio — Install To First Real Answer (04:50)
17. Lab LM Studio's Local Server — Your Laptop As An AI Server (04:48)
18. Lab Ollama — Pull, Run, And The API On 11434 (05:08)
19. Under The Hood llama.cpp And MLX (05:12)
20. On-Device AI Edge, LiteRT-LM, Edge Gallery (05:11)

5 - Your First Local Workflow
21. The Folder Pattern One Folder, One Model, One Output (04:58)
22. Lab Building The Customer-Notes Reviewer (04:39)
23. Lab Prompt, Examples, Checklist (04:44)
24. Artifacts Beat Chat Answers (04:43)
25. Lab Run It Ten Times — Finding Where It Breaks (04:39)

6 - Evals, Hybrid, and Knowing When to Stop
26. What An Eval Actually Is (04:50)
27. Lab A Real Eval On The Same Ten Files (04:38)
28. The Hybrid Pattern Local, Cloud, Human (05:25)
29. Privacy, Residency, And What Never Leaves (05:13)
30. Workflows Before Fine-Tuning (04:56)

7 - Where the Businesses Are
31. The Opportunity Filter (05:30)
32. Idea 1 — A Local QA Reviewer For Home Health (05:11)
33. Idea 2 — An Offline Field-Report Copilot (05:09)
34. Idea 3 — A Pre-Send Reviewer For Professional Services (05:18)
35. Service First, Product Second (04:32)
36. The 24-Month Window — Picking Your Vertical (05:17)

8 - Capstone — Build Your Local AI Lab
37. Lab Setting Up Your Local AI Lab Folder (04:46)
38. Lab Capstone Walkthrough — Ten Files, One Artifact (04:35)
39. Lab Local Embeddings And Search Over Your Files (04:36)
40. Where To Go Next (04:48)
[/spoiler]
Файлы примеров: не предусмотрены
Формат видео: MP4
Видео: AVC, 1920x1080, 16:9, 30fps, 2127kbps
Аудио: AAC, 44.1Hz, 128kbps, stereo
[spoiler="Скриншоты"]








[/spoiler]