workflowstacks
ai-agent

Airllm

AirLLM 70B inference with single 4GB GPU
33,751 stars3,555 forksJupyter NotebookUpdated 9/6/2026100% free · open source
What it does

AirLLM 70B is an AI model that allows you to run large language models on a single 4GB GPU for inference, enabling you to generate human-like text and respond to questions and prompts

When to use it
  • •When you need to deploy a language model for a startup project but have limited GPU resources
  • •When you want to test and fine-tune a large language model without incurring high cloud costs
  • •When you require a local, self-hosted language model solution for privacy or security reasons
Ready-to-paste prompt
python inference.py --model-name airllm-70b --prompt 'Write a short story about a character who discovers a hidden world.'
Heads up: Make sure you have a compatible GPU with at least 4GB of VRAM and a CUDA version compatible with the PyTorch requirements of the project to avoid runtime errors
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/airllm && curl -fsSL https://workflowstacks.com/api/skills/airllm/claude-skill -o ~/.claude/skills/airllm/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 Airllm works
Codeflow
Free to inspect

Airllm is a medium Jupyter Notebook project (~7.6k lines across 34 code files, plus 6 test files). Expect some technical setup — comfortable with a terminal, or ask a developer. Last commit this month, Apache-2.0 license, has a test suite.

Size
Medium codebase
~7.6k lines · 34 code files · ~1 h to skim
Setup
Some technical setup
Comfortable with a terminal? 20–40 min. Otherwise ask a dev.
Runs on
Python
No API keys detected
Jupyter Notebook 95%Python 4%
Where to start reading
  1. 1
    README.md
    Start here — what it does and how to install it
  2. 2
    requirements.txt
    Dependencies and the commands it exposes
  3. 3
    air_llm/__init__.py
    Inside air_llm/ — the main logic begins here
  4. 4
    examples/inferrence.ipynb
    A worked example — copy this to get going
What's in each folder
air_llm/Core code — the actual logic40 files
examples/Examples you can copy1 files
anima_100k/Folder8 files
rlhf/Folder7 files
training/Folder5 files
data/Data files2 files
scripts/Helper scripts2 files
eval/Evaluations & benchmarks1 files
READMEHas testsDocumentedCI checksExamples includedApache-2.0 licenseUpdated this month
Quick Actions
Details
Creator
lyogavin
Language
Jupyter Notebook
Category
ai-agent
Published
6/12/2023

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

Related skills

More ai-agent tools founders pair with this one.

ai-agent★ 276,806
Track GitHub Stars with 996.ICU
Get a popular GitHub star counter for your startup, ideal.
ai-agent★ 264,191
Superpowers
An agentic skills framework & software development methodology that works.
ai-agent★ 244,424
Linux: Open Source Kernel
Get the Linux kernel source tree for custom development, ideal for startup founders in need of a flexible OS foundation
ai-agent★ 210,750
Vue
This is the repo for Vue 2. For Vue 3, go to https://github.com/vuejs/core
ai-agent★ 204,069
Improve Code with andrej-karpathy-skills
Get better code behavior with andrej-karpathy-skills, 165k+ GitHub stars, for founders using LLMs.
ai-agent★ 197,010
FreeDomain: Free Website Domain
Get a free domain with FreeDomain.