Build and deploy MCP servers
Create Model Context Protocol servers that give AI models access to your tools, data, and services.
Dev Tools · Project · Intermediate · 90 min · MCP SDK, TypeScript, Python +1
Dev ToolsIntermediateProject
Run AI models locally with edge inference
Set up local-first AI inference on your own hardware — no cloud, no API keys, full privacy.
90 minOllama, llama.cpp, vLLM10xCareer Team
Choose your training style
Pick the format that matches the level of support you want.
Self-pacedAvailable
Self-paced
Start immediately and work through the training on your own schedule.
Free
Human trainerComing soon
Human trainer
Join a guided cohort or workshop format when live delivery is available.
$99
Guided by an instructor
AI trainerComing soon
AI trainer
Practice with an AI-guided trainer experience tailored to the course topic.
$9
Personalized guidance
What you'll learn
- Run open-weight LLMs on your own hardware
- Choose appropriate model sizes and quantization for your use case
- Serve local models via OpenAI-compatible APIs
- Evaluate trade-offs between local and cloud inference
Tags
local-aiedgeinferenceprivacyopen-weighttrending
Overview
Local-first edge AI inference lets you run powerful models on your own machine or edge devices. With 633K+ stars across the ecosystem, tools like llama.cpp, Ollama, and vLLM have made this accessible to everyone.
What you'll build
- A local inference setup running open-weight models
- A private AI assistant that never sends data to the cloud
- A benchmark comparison across different quantization levels
What you'll learn
- Choosing the right model: size vs. quality vs. hardware requirements
- Quantization: what it is and how to pick the right level (Q4, Q5, Q8)
- Setting up Ollama or llama.cpp on your machine
- Serving models via OpenAI-compatible local APIs
- When local beats cloud (and vice versa)
Why this matters
Privacy-sensitive work, offline environments, and cost control all demand local inference skills. This is a must-know for anyone serious about AI.
Related
Related trainings
Build document parsing & Markdown pipelines
Extract, transform, and structure content from PDFs, DOCX, HTML, and more into clean Markdown for AI consumption.
Dev Tools · Project · Intermediate · 75 min · Docling, MarkItDown, Unstructured +1
Build with Claude Code & Codex CLI wrappers
Extend AI coding assistants with custom wrappers, hooks, and workflows — the fastest-growing segment in dev tools.
Dev Tools · Project · Advanced · 90 min · Claude Code, Codex CLI, Git +1
Career signals, without the noise.
A few useful emails a month — hiring shifts, skills that move interviews, and what to do next.
Prefer the feed? Follow 10xCareer on LinkedIn