airllm vs LLMs-from-scratch

A neutral, constraint-first comparison - live GitHub stats and typed relationships, not marketing.

airllmLLMs-from-scratch
TaglineRepository for running large language models with reduced memory usage on limited GPU hardware.Implement a ChatGPT-like LLM in PyTorch from scratch
Stars22k99k
Forks2.6k15k
Open issues1064
LanguageJupyter NotebookJupyter Notebook
LicenseApache-2.0Other
Last pushedJul 7, 2026Jun 2, 2026
CategoriesModel Training, Inference & ServingModel Training, LLM Frameworks

airllm

AirLLM allows efficient inference of large language models like 70B parameter sizes using only a single 4GB GPU, without applying techniques such as quantization, distillation, or pruning. It supports various large-scale models and enhances performance capabilities through continuous updates focusing on model optimizations.

Jupyter Notebook

LLMs-from-scratch

Repository containing code and instructions for developing, pretraining, and finetuning a GPT-like large language model (LLM) using PyTorch.

Jupyter Notebook