#
airllm
Here are 5 public repositories matching this topic...
Run 70B+ LLMs on a single 4GB GPU — no quantization required.
-
Updated
Feb 28, 2026 - Python
Custom ML architectures, training pipelines, and Dockerized deployment experiments — built from scratch. Ongoing.
docker benchmarking machine-learning deep-learning pytorch custom-architecture nvidia-cuda mlops inference-optimization airllm
-
Updated
Jul 9, 2026
Improve this page
Add a description, image, and links to the airllm topic page so that developers can more easily learn about it.
Add this topic to your repo
To associate your repository with the airllm topic, visit your repo's landing page and select "manage topics."