design

Tiny LLM

Learn LLM inference system on Apple Silicon for systems engineers: build a tiny vLLM + Qwen
4,551 stars378 forksPythonUpdated 9/8/2026100% free · open source
What it does

Tiny-llm is a course that teaches systems engineers how to serve LLM inference on Apple Silicon by building a tiny vLLM and Qwen.

When to use it
  • When you need to deploy LLM models on Apple devices
  • When you want to optimize LLM serving for low-latency and efficiency
  • When you're a systems engineer looking to learn about LLM inference on Apple Silicon
Ready-to-paste prompt
python example.py --model tiny_vllm --input "What is the meaning of life?"
Heads up: Make sure you have the necessary dependencies and tools installed, including Python and the required libraries, and that your system meets the requirements for Apple Silicon support
Saves to your device
Use with Claude
New

Skip the builder — one click puts this in Claude, Cursor, Antigravity and more.

🛠️ Technical setup

Expect 20–40 minutes in a terminal — or let your AI agent drive it.

Try it instantly — no install
Claude Code
mkdir -p ~/.claude/skills/tiny-llm && curl -fsSL https://workflowstacks.com/api/skills/tiny-llm/claude-skill -o ~/.claude/skills/tiny-llm/SKILL.md
Open in another AI app

Opens the app with this repo with the prompt ready to go — no copy-paste needed.

Connect the whole catalog (MCP)
claude mcp add --transport http workflowstacks https://workflowstacks.com/api/mcp

Adds a WorkflowStacks connector to Claude Code: search and load any skill here by chatting.

How Tiny LLM works
Codeflow
Free to inspect

Tiny LLM is a large Python project (~23k lines across 145 code files, plus 2 test files). It is a full software project: use it through its install path rather than reading it end to end. Last commit this month, Apache-2.0 license, has a test suite.

Size
Large codebase
~23k lines · 145 code files · ~3 h to skim
Setup
Developer setup
A real software project. Use it via its install path; don't expect to read it all.
Runs on
Python
No API keys detected
Python 83%C++ 9%Metal 7%
Where to start reading
  1. 1
    README.md
    Start here — what it does and how to install it
  2. 2
    AGENTS.md
    The instructions the AI actually follows
  3. 3
    main.py
    Where the program starts running
  4. 4
    pyproject.toml
    Dependencies and the commands it exposes
  5. 5
    src/tiny_llm_ref/__init__.py
    Inside src/ — the main logic begins here
What's in each folder
src/Core code — the actual logic93 files
docs/Documentation1 files
benchmark_results/Folder102 files
book/Folder61 files
tests_refsol/Folder37 files
benches/Folder15 files
scripts/Helper scripts3 files
tests/Tests — proof it works3 files
READMEHas testsDocumentedCI checksApache-2.0 licenseUpdated this month
Quick Actions
Details
Creator
skyzh
Language
Python
Category
design
Published
4/19/2025

Are you the creator of this tool? Claim your listing → and earn 85% of every sale.