General Chat🔧 Supports Agent Tools
Llama 3.2 (1B)
onnx-community/Llama-3.2-1B-Instruct
Overview
Meta's official 1B parameter model optimized specifically for edge devices, mobile, and client-side web applications.
Parameters
1.2B
Quantization
q4f16
Footprint
~750 MB
Context Window
128K tokens
Browser Requirements & Caching
When you initiate a chat session using this model, your browser will download the model files directly from Hugging Face. The model will then be cached locally in your browser's Cache Storage API so subsequent loads are instant and run directly in the browser.
Tip: Ensure you have at least 1125 MB of free disk space for smooth initialization.