> For the complete documentation index, see [llms.txt](https://docs.ionos.com/cloud/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.ionos.com/cloud/ai/ai-model-studio/base-models.md).
# Base Models
{% hint style="info" %}
**Fair-use limits:** To ensure a reliable experience for all users, the AI Model Studio is subject to the following fair-use limits:
* **Parallel training:** Usage is limited to one active training process per user.
* **Inference capacity:** Limited to a maximum of three parallel queries per user.
* **Synthetic data generation:** Generation is limited to a maximum of 100 units per operation, with one parallel generation process allowed.
To increase the limits, contact [IONOS Cloud Support](https://docs.ionos.com/cloud/support/).
{% endhint %}
While fine-tuning can be applied to all kinds of AI models, it benefits the most when used with smaller and medium-sized models, elevating them to a level far beyond what was previously possible. Therefore, we currently only offer smaller models for fine-tuning, with the prospect of expanding the service to include larger models in the future. This page provides a detailed list of available models, their origin, and capabilities.
## Active Models
**Qwen3 0.6B:** Ultra-efficient model for text generation, translation, and conversational AI across 100+ languages. Ideal for chatbots, content creation, and multilingual support.
* **Languages:** 100+ languages (English, Chinese, French, Spanish, German, etc.)
* **Data Types:** Text
* **Typical Use Cases**: Quick Text Classification, Content Moderation Filter, and High-Volume Data Tagging
**Qwen3 1.7B:** Powerful model for complex reasoning, mathematical computations, code generation, and multi-turn dialogues. Perfect for role-playing, logical problem-solving, and instruction following.
* **Languages:** 100+ languages (English, Chinese, French, Spanish, German, etc.)
* **Data Types:** Text
* **Typical Use Cases:** Complex Instruction Following, Automated Code/Formula Generation, and Troubleshooting Agent Reasoning.
**Qwen2-VL 2B Instruct:** State-of-the-art multimodal vision-language model for image understanding, video analysis, and visual question answering. Handles images of various resolutions and ratios, supports multilingual text in images, and excels at visual reasoning tasks. Supports multiple input types including local files, URLs, and base64 images.
* **Languages:** 100+ languages (English, Chinese, most European, Japanese, Korean, Arabic, Vietnamese, etc.)
* **Data Types:** Image, Text, Video
* **Typical Use Cases:** Visual Data Extraction (OCR), Manufacturing Quality Inspection, Reading Gauges and Meters
**Granite 3.3 Micro:** Long-context specialist for document summarization, text classification, question-answering, and code generation. Excels at analyzing lengthy documents and extracting information with 128k context window. ISO 42001 certified.
* **Languages:** English, German, Spanish, French, Japanese, Portuguese, Arabic, Czech, Italian, Korean, Dutch, and Chinese
* **Data Types:** Text
* **Typical Use Cases:** Long-Form Summarization, Legal/Compliance Document Q\&A, and Technical Document Categorization
---
# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.
## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.
Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter:
```
GET https://docs.ionos.com/cloud/ai/ai-model-studio/base-models.md?ask=&goal=
```
`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.
Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.