Xenna/gemma-4-e4b-it

Gemma 3 4B-IT (LiteRT-LM)

Gemma 3 4B-IT by Google — Quantized as a LiteRT-LM task (.task) for on-device inference.

Model Details

• Base model: Gemma 3 4B-IT by Google
• Format: LiteRT-LM task (.task)
• Quantized: INT8
• Size: ~3.7 GB
• Use case: Chat on mobile devices (AI Chat task only)
• Runtime: LiteRT-LM on-device (no cloud)

Usage

Deploy the model using any compatible LiteRT runtime.

Or via Hugging Face Hub:

huggingface-cli download Xenna/gemma-4-e4b-it --local-dir ./models/gemma-4-e4b-it