google-deepmind / google-deepmind/gemma

DOC: Add more specific GPU examples to System Requirements in README.md

Open
#395 6 comments 0 reactions 0 assignees View on GitHub
Dominant language
Python
Stars
5.7k
Forks
1k
Avg merge
10h 33m
Merged PRs (30d)
2

Description

The current README.md for the gemma repository provides GPU VRAM recommendations for the 2B and 7B checkpoints. However, it only states the required memory (e.g., "8GB+ RAM" and "24GB+ RAM") without providing any examples of common hardware that meets these specifications.

This can make it difficult for new users to quickly assess if their machine is capable of running the models, requiring them to search for external information on GPU memory specifications.

Proposed Solution:

I suggest updating the System Requirements section to include a few examples of popular GPUs that meet the VRAM recommendations. This would make the requirements more concrete and immediately understandable for users.

Example of proposed text:
... For GPU, we recommend 8GB+ RAM on GPU for The 2B checkpoint and 24GB+ RAM on GPU are used for the 7B checkpoint. For reference, GPUs with 8GB+ VRAM include models like the NVIDIA RTX 3060, while models with 24GB+ VRAM include the NVIDIA RTX 4090 and AMD Radeon RX 7900 XTX.

I believe this small addition would significantly improve the user experience. I'm happy to create a pull request to implement this change once a maintainer confirms this is a welcome contribution.

Contributor guide

Open the contributing guide

Assessment

This issue has not been assessed yet.

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.