Models Comparison

AI Model Hub for Free: From December 1, 2024, to September 30, 2025, IONOS is offering all foundation models in the AI Model Hub for free. Create your contract today and kickstart your AI journey!

This comprehensive comparison table shows all currently active foundation models in the IONOS AI Model Hub, providing essential information about their capabilities, modalities, and features at a glance. Click on each model name to access detailed summaries and specifications.

Features overview

The following table provides a comprehensive comparison of all active foundation models currently available in the AI Model Hub:

Model Name	Type	Input Modality	Output Modality	Streaming	Tool Calling	Model Size
Mistral Nemo 12B	Language Model	Text	Text	✅	✅	Small
Llama 3.1 8B	Language Model	Text	Text	✅	✅	Small
Teuken 7B	Language Model	Text	Text	✅	❌	Small
Mistral Small 24B	Language Model	Text, Image	Text	✅	✅	Medium
Llama 3.3 70B	Language Model	Text	Text	✅	✅	Medium
GPT-OSS 120B	Language Model	Text	Text	✅	❌	Medium
Llama 3.1 405B	Language Model	Text	Text	✅	✅	Large
Code Llama 13B	Coding Model	Text	Text	✅	❌	Medium
BGE Large v1.5	Embedding Model	Text	Vector	❌	❌	-
BGE m3	Embedding Model	Text	Vector	❌	❌	-
Paraphrase Multilingual MPNet v2	Embedding Model	Text	Vector	❌	❌	-
FLUX.1-schnell	Image Generation	Text	Image	❌	❌	-
Stable Diffusion XL	Image Generation	Text	Image	❌	❌	-

Understanding Model categories

The IONOS AI Model Hub offers three distinct categories of foundation models, each optimized for specific use cases:

Large Language Models

Small Models (Less than 15 billion parameters)

Small language models are optimized for fast inference and low resource consumption. They are ideal for real-time applications and scenarios where latency and cost are critical.

Medium Models (15 billion to 150 billion parameters)

Medium-sized models provide a strong balance between response quality and inference speed. They are suitable for applications that demand higher accuracy and more nuanced language understanding.

Large Models (More than 150 billion parameters)

Large models are designed for maximum language understanding, deep reasoning, and high-quality responses. They are best suited for advanced applications where accuracy and depth of knowledge are paramount.

Embedding Models

Embedding models convert text into dense vector representations, enabling semantic search, clustering, and similarity comparison. They are essential for building search engines, recommendation systems, and knowledge retrieval applications.

Text-to-Image Models

Text-to-image models generate images from textual descriptions, supporting creative and generative AI use cases such as content creation, design, and prototyping.