Azion Edge AI Models

Azion’s edge-optimized models span multiple AI domains including text generation, image analysis, embeddings, and more. Each model is designed to balance performance and resource efficiency for edge deployment.

This page provides a list of models available for use with Edge AI. To learn more about it, visit the Edge AI Reference.

Available Models

E5 Mistral 7B Instruct

The E5 Mistral 7B Instruct model is optimized for English text embedding tasks, with capabilities for multilingual processing, flexible customization, and handling long input sequences, making it suitable for complex natural language processing applications.

Mistral 3 Small (24B AWQ)

This is a language model that delivers capabilities comparable to larger models while being compact. It is ideal for conversational agents, function calling, fine-tuning, and local inference with sensitive data.

Gemma3

Gemma 3 is a model designed for fast deployment on devices, offering advanced capabilities such as multilingual support, text and visual reasoning, expanded context windows, function calling, and quantized models for high performance.

BAAI/bge-reranker-v2-m3

A lightweight reranker model with strong multilingual capabilities. It offers multilingual support and it’s easy to deploy, with fast inference.

Florence 2 Large

Florence 2 is an advanced vision foundation model that leverages a prompt-based approach and a massive dataset to excel in various vision and vision-language tasks.

Qwen2.5 VL AWQ 3B

A Vision Language Model (VLM) that offers advanced capabilities such as visual analysis, agentic reasoning, long video comprehension, visual localization, and structured output generation.

Qwen2.5 VL AWQ 7B

A Vision Language Model (VLM) that supports 7 billion parameters, offering advanced capabilities such as visual analysis, agentic reasoning, long video comprehension, visual localization, and structured output generation.