airllm vs LLMs-from-scratch
A neutral, constraint-first comparison - live GitHub stats and typed relationships, not marketing.
| airllm | LLMs-from-scratch | |
|---|---|---|
| Tagline | Repository for running large language models with reduced memory usage on limited GPU hardware. | Implement a ChatGPT-like LLM in PyTorch from scratch |
| Stars | 22k | 99k |
| Forks | 2.6k | 15k |
| Open issues | 106 | 4 |
| Language | Jupyter Notebook | Jupyter Notebook |
| License | Apache-2.0 | Other |
| Last pushed | Jul 7, 2026 | Jun 2, 2026 |
| Categories | Model Training, Inference & Serving | Model 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