⬢github first seen 1 d ago, last 6 min ago, peak #7
AirLLM runs large language model inference on a single 4GB GPU
Original: lyogavin/airllm
A developer project called AirLLM is drawing attention for enabling inference on a 2.8 trillion parameter language model using only a single GPU with 4GB of memory. The open-source tool, written as a Jupyter Notebook, drastically lowers the hardware barrier for running very large models locally, making it a notable talking point among AI developers.
Why now: Running a 2.8 trillion parameter model on a 4GB GPU would be a major accessibility breakthrough for local LLM inference.
Rank over time, top of the chart is #1. 96 snapshots from 23 h ago to 6 min ago.
Evidence
- lyogavin/airllm · lyogavin · 16
AirLLM 2.8T LLM inference with single 4GB GPU
API: https://socialmediatrends-api.osmike.com/v1/trends/1850728