AirLLM Files

AirLLM 70B inference with single 4GB GPU

This is an exact mirror of the AirLLM project, hosted at https://github.com/lyogavin/airllm. SourceForge is not affiliated with AirLLM.

The interactive file manager requires Javascript. Please enable it or use sftp or scp.
You may still browse the files here.

Name	Modified	Size	InfoDownloads / Week
Parent folder
AirLLM v3.0.1 source code.tar.gz	2026-06-30	2.3 MB	0
AirLLM v3.0.1 source code.zip	2026-06-30	2.4 MB	2
README.md	2026-06-30	486 Bytes	0
Totals: 3 Items		4.7 MB	2

AirLLM v3.0.1

Patch release.

Fix: import airllm failed on a clean install with ModuleNotFoundError: No module named 'sentencepiece'. sentencepiece is now a declared dependency, so pip install airllm works out of the box.
Model-family imports are now defensive: a missing optional dependency for one niche model family no longer breaks the whole package — the generic streaming path always loads.

Upgrade

:::bash
pip install --upgrade airllm

Source: README.md, updated 2026-06-30

Other Useful Business Software

MongoDB Atlas runs apps anywhere

Deploy in 115+ regions with the modern database for every enterprise.

MongoDB Atlas gives you the freedom to build and run modern applications anywhere—across AWS, Azure, and Google Cloud. With global availability in over 115 regions, Atlas lets you deploy close to your users, meet compliance needs, and scale with confidence across any geography.

Start Free

Fully Managed MySQL, PostgreSQL, and SQL Server

Automatic backups, patching, replication, and failover. Focus on your app, not your database.

Cloud SQL handles your database ops end to end, so you can focus on your app.

Try Free

$300 Free Credits for Your Google Cloud Projects

Start building on Google Cloud with $300 in free credits. No commitment, no credit card required until you're ready to scale.

Launch your next project with $300 in free Google Cloud credits—no strings attached. Test, build, and deploy without risk. Use your credits across the entire Google Cloud platform to find what works best for your needs. After your credits are used, continue with always-free tier services. Only pay when you're ready to scale. Sign up in minutes and start exploring.

Start Free Trial

Recommended Projects

Colibrì
Run GLM-5.2 (744B MoE) on a 25GB-RAM consumer machine
uzu
A high-performance inference engine for AI models
shimmy
Python-free Rust inference server
qvac-fabric-llm.cpp
QVAC Fabric: cross-platform LLM inference and fine-tuning
bitsandbytes
Accessible large language models via k-bit quantization for PyTorch

AirLLM Files

AirLLM 70B inference with single 4GB GPU

Get an email when there's a new version of AirLLM

AirLLM v3.0.1

Upgrade