EDU-KI-RLP: Available AI Models

Codestral 22B was developed by Mistral AI specifically for the goal of code completion.
It was trained on more than 80 different programming languages, including Python, SQL, bash, C++, Java, and PHP.
It uses a context window of 32k for evaluation of large code generating, and can fit on one GPU of our cluster.

Gemma is Google’s family of light, open-weights models developed with the same research used in the development of its commercial Gemini model series.
Gemma 3 27B Instruct is quite fast and thanks to its support for vision (image input), it is a great choice for all sorts of conversations.

In August 2025 OpenAI released the gpt-oss model series, consisting of two open-weight LLMs that are optimized for faster inference with state-of-the-art performance across many domains, including reasoning and tool use.
According to OpenAI, the gpt-oss-120b model achieves near-parity with OpenAI o4-mini on core reasoning benchmarks.

Meta LLaMA 3.1 is the most lightweight with the fastest performance and good results across all benchmarks.
It is sufficient for general conversations and assistance.

SauerkrautLM is trained by VAGOsolutions on Llama 3.1 70B specifically for prompts in German.

Achieves good overall performance, on par with GPT-4, but with a much larger context window and more recent knowledge cutoff.
Best in English comprehension and further linguistic reasoning, such as translations, understanding dialects, slang, colloquialism and creative writing.

MedGemma 27B Instruct is a variant of Gemma 3 suitable for medical text and image comprehension.
It has been trained on a variety of medical image data, including chest X-rays, dermatology images, ophthalmology images, and histopathology slides, as well as medical text, such as medical question-answer pairs, and FHIR-based electronic health record data.
MedGemma variants have been evaluated on a range of clinically relevant benchmarks to illustrate their baseline performance.

Developed by Mistral AI, Mistral Large Instruct 2407 is a dense language model with 123B parameters.
It achieves great benchmarking scores in general performance, code and reasoning, and instruction following.
It is also multi-lingual and supports many European and Asian languages.

Qwen 2.5 Coder 32B Instruct is a code-specific LLM based on Qwen 2.5.
It has one of the highest scores on code-related tasks, on par with OpenAI’s GPT-4o, and is recommended for code generation, code reasoning and code fixing.

A powerful Vision Language Model (VLM) with competitive performance in both langauge and image comprehension tasks.

Qwen 3 32B is a large dense model developed by Alibaba Cloud released in April 2025.
It supports reasoning and outperforms or is at least on par with other state-of-the-art reasoning models such as OpenAI o1 and DeepSeek R1.

Developed by Alibaba Cloud, QwQ is the reasoning model of the Qwen series of LLMs.
Compared to non-reasoning Qwen models, it achieves significnatly higher performance in tasks that require problem-solving.
QwQ 32B is lighter and faster than DeepSeek R1 and OpenAI’s o1, but achieves comparable performance.

OpenGPT-X is a research project funded by the German Federal Ministry of Economics and Climate Protection (BMWK) and led by Fraunhofer, Forschungszentrum Jülich, TU Dresden, and DFKI.
Teuken 7B Instruct Research v0.4 is an instruction-tuned 7B parameter multilingual LLM pre-trained with 4T tokens, focusing on covering all 24 EU languages and reflecting European values.

Apertus by Swiss AI is a fully open-source language model supporting over 1000 languages. It was trained on 15T tokens and uses a new xIELU activation function.

GLM-4.7 by Z.ai is a powerful language model with strong capabilities in coding, complex reasoning and tool use. It offers improved UI design and supports Interleaved Thinking and Preserved Thinking.

InternVL 3.5 by OpenGVLab is an open-source multimodal model with vision capabilities. It uses Cascade Reinforcement Learning and a Visual Resolution Router for better performance and 4x inference speedup.

Qwen 3 VL by Alibaba Cloud is a powerful vision-language model with GUI interaction, video understanding and enhanced OCR in 32 languages. It supports a native 256K context.

Qwen 3 Omni by Alibaba Cloud is a natively end-to-end multimodal model that processes text, images, audio and video and delivers real-time streaming responses in text and speech. It supports 119 text and multiple audio input/output languages.