@danielhanchen on Hugging Face: "Gemma 3n finetuning is now 1.5x faster and uses 50% less VRAM in Unsloth!…"

Join the conversation

Join the community of Machine Learners and AI enthusiasts.

danielhanchen

posted an update 5 days ago

Post

2214

Gemma 3n finetuning is now 1.5x faster and uses 50% less VRAM in Unsloth!

Click "Use this model" and click "Google Colab"!

unsloth/gemma-3n-E4B-it

unsloth/gemma-3n-E2B-it

https://colab.research.google.com/github/unslothai/notebooks/blob/main/nb/Gemma3N_(4B)-Conversational.ipynb

5 days ago

unsloth ftw

·

5 days ago

Thank you!

In this post