Base Models

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.

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