AI Model Registry

Explore and manage local models tested for compatibility. These options are provided as recommendations to run client-side with WebGPU acceleration.

Detecting your hardware…

Qwen 2.5 (0.5B)

onnx-community/Qwen2.5-0.5B-Instruct

General Chat🔧 Agent Tools

A highly capable, extremely lightweight model. An excellent balance of size and intelligence for fast browser inference.

Params: 0.5BContext: 128KQuant: q4Size: ~250 MB
Details

Llama 3.2 (1B)

onnx-community/Llama-3.2-1B-Instruct

General Chat🔧 Agent Tools

Meta's official 1B parameter model optimized specifically for edge devices, mobile, and client-side web applications.

Params: 1.2BContext: 128KQuant: q4Size: ~600 MB
Details

TinyLlama (1.1B)

Xenova/TinyLlama-1.1B-Chat-v1.0

General Chat

A highly popular, compact model trained on 3 trillion tokens. A great baseline for testing web-based LLMs.

Params: 1.1BContext: 2KQuant: q4Size: ~550 MB
Details

Qwen 2.5 Coder (0.5B)

onnx-community/Qwen2.5-Coder-0.5B-Instruct

Code Generation🔧 Agent Tools

A version of Qwen 2.5 specifically fine-tuned for writing, understanding, and debugging code in the browser.

Params: 0.5BContext: 128KQuant: q4Size: ~250 MB
Details

Phi-3.5 Mini

onnx-community/Phi-3.5-mini-instruct

Advanced Reasoning🔧 Agent Tools

Microsoft's highly intelligent edge model. It requires significantly more browser memory but punches well above its weight class.

Params: 3.8BContext: 128KQuant: q4Size: ~1900 MB
Details