Manual Download: Gemma 3 1B Instruct

​

Why Manual Download?

1. Have a Hugging Face account
2. Accept the Gemma license agreement
3. Use authenticated downloads

​

Prerequisites

​

Create a Hugging Face Account

​

Accept the Gemma License

1. Visit the Gemma 3 1B model page
2. Click Agree and access repository
3. Read and accept the license terms

Note: License approval is usually instant but may take a few minutes.

​

Step 1: Install Hugging Face CLI

pipx install huggingface_hub

python3 -m pip install --upgrade "huggingface_hub[cli]"

​

Step 2: Authenticate

huggingface-cli login

1. Go to huggingface.co/settings/tokens
2. Create a new token with Read permissions
3. Paste the token into your terminal

huggingface-cli whoami

​

Step 3: Download the Model

​

macOS

huggingface-cli download google/gemma-3-1b-it \
  --repo-type model \
  --local-dir "$HOME/Library/Application Support/izwi/models/Gemma-3-1b-it"

​

Linux

huggingface-cli download google/gemma-3-1b-it \
  --repo-type model \
  --local-dir "$HOME/.local/share/izwi/models/Gemma-3-1b-it"

​

Windows (PowerShell)

huggingface-cli download google/gemma-3-1b-it `
  --repo-type model `
  --local-dir "$env:APPDATA\izwi\models\Gemma-3-1b-it"

​

Step 4: Verify Installation

izwi list --local

izwi models load Gemma-3-1b-it

​

Troubleshooting

​

”Access to model is restricted”

1. Visit huggingface.co/google/gemma-3-1b-it
2. Click Agree and access repository
3. Wait a few minutes for approval
4. Try the download again

​

”401 Client Error: Unauthorized”

1. Go to huggingface.co/settings/tokens
2. Create a new token with Read access
3. Run huggingface-cli login again with the new token

​

Model not appearing in Izwi

1. Check the model was downloaded to the correct directory
2. Verify the folder name is exactly Gemma-3-1b-it
3. Restart the Izwi server

​

Download interrupted

​

Using Gemma 3 1B

izwi chat --model Gemma-3-1b-it

​

See Also

• Models Overview
• Manual Download Guide
• Troubleshooting