Skip to content
English

Switch theme

Discover▾

Not sure where to start? This week’s hottest software, models and stacks in three minutes.

AI Apps▾

AI software people use: from assistants like ChatGPT to tools for coding, video and workflows, picked by purpose.

For Agents▾

Software for AI: tools that let your agent (Claude Code, Codex, Cursor…) browse, read docs, run code and remember.

Models▾

Choose models, estimate cost, self-host: prices, rankings, benchmarks, free tiers and compute.

Solutions▾

A goal or an error message? Ready-made stacks, steps and fixes by scenario.

Learn▾

A systematic course from zero to the frontier, with an algorithm library, must-read papers and tutorials.

Frontier▾

Daily AI news, weekly highlights, the latest papers and how AI is changing every discipline.

Inference & Deployment

Running LLMs on Your Own Computer

Memory math, quantised models and desktop apps for private, offline AI.

Intermediate 15 min For: Beginners / Developers ✎ In progress

🖥️Self-hosted computeVRAM calculator and tier guide (moved to Self-hosted compute)→

✎ This lesson is still being written. Below is the planned outline; it is not indexed by search engines yet.

What this lesson will cover

  1. How much memory a model needs
  2. Choosing a quantisation
  3. Desktop apps and CLIs
  4. Privacy and licences

Software used in this lesson

Ollama Local inference & servingv0.40.8 ★ 184k Get up and running with Kimi, GLM, MiniMax, DeepSeek, gpt-oss, Qwen, Gemma and other models. Open source CLIAPI LM Studio Local inference & serving0.4.26（Homebrew 当前） Desktop app to download and run local LLMs with an OpenAI-compatible server. Closed / commercial Free macOSWindowsLinux jan AI apps & chat clientsv0.8.6 ★ 45k Jan is an open source alternative to ChatGPT that runs 100% offline on your computer. Open source AppAPI mlx-lm Local inference & serving ★ 7.4k Run LLMs with MLX Open source

Part of these paths

① Beginner Path: Understand AI② Developer Path: Build AI Apps & Agents

Data updated: Learn AI curriculum · Lesson news(UTC+8)