⬢github first seen 11 h ago, last 11 min ago, peak #7
AirLLM runs 70B models on a 4GB GPU
Original: lyogavin/airllm
A new open-source project called AirLLM enables inference of 70-billion-parameter large language models on a single consumer GPU with only 4GB of memory. The Jupyter Notebook-based tool, hosted on GitHub, is drawing attention for dramatically lowering the hardware barrier to running top-tier open models locally, potentially letting hobbyists and developers experiment with large models without expensive data-center GPUs.
Why now: Running a 70B parameter model on such minimal hardware would be a major breakthrough for local AI inference, sparking interest among developers.
Rank over time, top of the chart is #1. 48 snapshots from 11 h ago to 11 min ago.
Evidence
- lyogavin/airllm · lyogavin · 16
AirLLM 70B inference with single 4GB GPU
API: https://socialmediatrends-api.osmike.com/v1/trends/1850728