lyogavin/airllm
Position in GitHub’s trending lists, facts from the GitHub API and the README, and the star history recorded by this site.
Collected
AirLLM 70B inference with single 4GB GPU
First paragraph of the README
AirLLM dramatically reduces inference memory usage, letting 70B large language models run on a single 4GB GPU card — without quantization, distillation, or pruning.
Install command found in the README
pip install airllmWhere it is trending
| List | Position | Stars gained |
|---|---|---|
| All languages, today | #7 | +541 today |
Star history recorded by this site
One reading per day since Oct 11, 2026, the first day this repository was seen in a trending list. A chart is drawn once three days have been recorded.
- 36,161
Positions, star totals and “stars gained” are the ones GitHub published, read at Oct 11, 2026, 13:50 UTC. The README paragraph and the install command are copied automatically and are not reviewed.
Source: github.com/trending · updated
More lists to explore
The same data cut by period, programming language and subject.
By period
By programming language, today
By subject
Questions and answers
More detail on the method page.
How many stars does lyogavin/airllm have?
36,161 stars and 3,793 forks when GitHub’s trending page was read on Oct 11, 2026, 13:50 UTC. GitHub reported 541 new stars for the period of the list it appears in.
What is lyogavin/airllm written in, and under which license?
GitHub classifies it as Jupyter Notebook. Its license, as reported by the GitHub API, is Apache-2.0.
How do I install lyogavin/airllm?
Its README gives this command: pip install airllm. It is copied automatically; check the repository before running it.