Run large AI models on a low-memory GPU, enabling advanced language processing without heavy hardware requirements.
From the README
pip install airllm
- Step 1. make sure you have bitsandbytes installed by pip install -U bitsandbytes
- Step 2. make sure airllm verion later than 2.0.0: pip install -U airllm
- Step 3. when initialize the model, passing the argument compression ('4bit' or '8bit'):
Excerpts from the project README on GitHub. Copyright and licensing remain with the respective authors.
Claim its page: indexed whatever its rank, translated into six languages, and enriched with what you write yourself.
Get an email alert on its next release or when it starts trending — never miss the moment.
Free · no card · unsubscribe anytimeAirLLM 70B inference with single 4GB GPU
airllm has 33.2k stars on GitHub. It has been forked 3.5k times. airllm is written mainly in Jupyter Notebook. It has been in active development since 2023. airllm is available under the Apache-2.0 license. Its main topics are chinese-llm, chinese-nlp, finetune, generative-ai.
What is airllm?
AirLLM 70B inference with single 4GB GPU
Is airllm open source?
airllm is an open-source project. It is released under the Apache-2.0 license.
Is airllm free?
Yes. airllm is free and open source — you can use, modify and self-host it.
What license does airllm use?
airllm is available under the Apache-2.0 license.
What language is airllm written in?
airllm is written mainly in Jupyter Notebook.
Add this live badge to your README — your GitHub stars and directory rank, refreshed daily.
[](https://olud.ai/project/lyogavin-airllm.html)
Measured from GitHub topics shared by both projects, weighted by how rare each topic is.