# Models Comparison

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

### Language and Coding Models

| **Model Name**                                                                                                                                                     | **Type**       | **Input Modality** | **Output Modality** | **Streaming** | **Tool Calling** | **Context Window** | **Model Size** |
| ------------------------------------------------------------------------------------------------------------------------------------------------------------------ | -------------- | :----------------: | :-----------------: | :-----------: | :--------------: | :----------------: | :------------: |
| [<mark style="color:blue;">**Mistral Nemo 12B**</mark>](https://docs.ionos.com/sections-test/guides/ai/ai-model-hub/models/llms/mistral-nemo)                      | Language Model |        Text        |         Text        |       ✅       |         ✅        |        128k        |      Small     |
| [<mark style="color:blue;">**Llama 3.1 8B**</mark>](https://docs.ionos.com/sections-test/guides/ai/ai-model-hub/models/llms/meta-llama-3-1-8b)                     | Language Model |        Text        |         Text        |       ✅       |         ✅        |        128k        |      Small     |
| [<mark style="color:blue;">**Teuken 7B**</mark>](https://docs.ionos.com/sections-test/guides/ai/ai-model-hub/models/llms/opengpt-x-teuken)                         | Language Model |        Text        |         Text        |       ✅       |         ❌        |         8k         |      Small     |
| [<mark style="color:blue;">**Mistral Small 24B**</mark>](https://docs.ionos.com/sections-test/guides/ai/ai-model-hub/models/llms/mistral-small-24b)                | Language Model |     Text, Image    |         Text        |       ✅       |         ✅        |        128k        |     Medium     |
| [<mark style="color:blue;">**Llama 3.3 70B**</mark>](https://docs.ionos.com/sections-test/guides/ai/ai-model-hub/models/llms/meta-llama-3-3-70b)                   | Language Model |        Text        |         Text        |       ✅       |         ✅        |        128k        |     Medium     |
| [<mark style="color:blue;">**GPT-OSS 120B**</mark>](https://docs.ionos.com/sections-test/guides/ai/ai-model-hub/models/llms/openai-gpt-oss-120b)                   | Language Model |        Text        |         Text        |       ✅       |         ✅        |        128k        |     Medium     |
| [<mark style="color:blue;">**Llama 3.1 405B**</mark>](https://docs.ionos.com/sections-test/guides/ai/ai-model-hub/models/llms/meta-llama-3-1-405b)                 | Language Model |        Text        |         Text        |       ✅       |         ✅        |        128k        |      Large     |
| [<mark style="color:blue;">**Code Llama 13B**</mark>](https://docs.ionos.com/sections-test/guides/ai/ai-model-hub/models/coding-models/meta-code-llama-13b)        | Coding Model   |        Text        |         Text        |       ✅       |         ❌        |         16k        |     Medium     |
| [<mark style="color:blue;">**Qwen3 Coder Next 80B**</mark>](https://docs.ionos.com/sections-test/guides/ai/ai-model-hub/models/coding-models/qwen3-coder-next-80b) | Coding Model   |        Text        |         Text        |       ✅       |         ✅        |        128k        |     Medium     |

### Embedding, Image Generation, and OCR Models

| **Model Name**                                                                                                                                                                                | **Type**         | **Input Modality** | **Output Modality** | **Max Input Length** |
| --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ---------------- | :----------------: | :-----------------: | :------------------: |
| [<mark style="color:blue;">**BGE Large v1.5**</mark>](https://docs.ionos.com/sections-test/guides/ai/ai-model-hub/models/embedding-models/bge-large-1-5)                                      | Embedding Model  |        Text        |        Vector       |      8192 tokens     |
| [<mark style="color:blue;">**BGE m3**</mark>](https://docs.ionos.com/sections-test/guides/ai/ai-model-hub/models/embedding-models/bge-m3)                                                     | Embedding Model  |        Text        |        Vector       |      8192 tokens     |
| [<mark style="color:blue;">**Paraphrase Multilingual MPNet v2**</mark>](https://docs.ionos.com/sections-test/guides/ai/ai-model-hub/models/embedding-models/paraphrase-multilingual-mpnet-v2) | Embedding Model  |        Text        |        Vector       |      128 tokens      |
| [<mark style="color:blue;">**FLUX.1-schnell**</mark>](https://docs.ionos.com/sections-test/guides/ai/ai-model-hub/models/image-generation-models/flux-1-schnell)                              | Image Generation |        Text        |        Image        |      256 tokens      |
| [<mark style="color:blue;">**LightOnOCR-2-1B**</mark>](https://docs.ionos.com/sections-test/guides/ai/ai-model-hub/models/ocr-models/lightonocr-2-1b)                                         | OCR              |        Image       |         Text        |      16k tokens      |

## 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 15B 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 (15B to 150B 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 150B 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.

### OCR models

Optical Character Recognition (OCR) models convert documents such as PDFs, scans, and images into clean, structured text. These vision-language models process visual content end-to-end, making them ideal for document digitization, data extraction, and content accessibility workflows.