Title: LLMs for German-language text %E2%80%94 LLM EU
Canonical: https://llmeu.com/da/use/german/
Markdown mirror: https://llmeu.com/da/use/german.md
Machine-readable: https://llmeu.com/llms.txt (index) - https://llmeu.com/llms-full.txt (full catalogue) - https://llmeu.com/llms-catalogue.json

# LLMs for German-language text

Models whose card records German among the languages it covers well or adequately. The card cites the source for that claim, or marks it unverified.

76 models %C2%B7 [Open in the catalogue filter](/da/models/?language=de)

- [Aya 23 8B](/da/models/aya-23-8b/) %E2%80%94 Cohere %C2%B7 8.03B %C2%B7 8K %C2%B7 cc-by-nc-4.0
- [Aya Expanse 8B](/da/models/aya-expanse-8b/) %E2%80%94 Cohere %C2%B7 8.03B %C2%B7 8K %C2%B7 cc-by-nc-4.0
- [Codestral 25.08](/da/models/codestral-25-08/) %E2%80%94 Mistral AI %C2%B7 128K %C2%B7 proprietary
- [Command A+ (05-2026)](/da/models/command-a-plus-05-2026/) %E2%80%94 Cohere %C2%B7 218.75B %C2%B7 128K %C2%B7 apache-2.0
- [Command R (08-2024)](/da/models/command-r-08-2024/) %E2%80%94 Cohere %C2%B7 32.3B %C2%B7 128K %C2%B7 cc-by-nc-4.0
- [DeepSeek-R1](/da/models/deepseek-r1/) %E2%80%94 DeepSeek %C2%B7 684.49B %C2%B7 128K %C2%B7 mit
- [DeepSeek-R1-Distill-Qwen-32B](/da/models/deepseek-r1-distill-qwen-32b/) %E2%80%94 DeepSeek %C2%B7 32.76B %C2%B7 128K %C2%B7 mit
- [DeepSeek-V3.2](/da/models/deepseek-v3-2/) %E2%80%94 DeepSeek %C2%B7 685.36B %C2%B7 160K %C2%B7 mit
- [DeepSeek-V4-Flash (0731)](/da/models/deepseek-v4-flash-0731/) %E2%80%94 DeepSeek %C2%B7 304.18B %C2%B7 1024K %C2%B7 mit
- [Devstral Small 2 (24B)](/da/models/devstral-small-2-24b/) %E2%80%94 Mistral AI %C2%B7 24.01B %C2%B7 256K %C2%B7 apache-2.0
- [EmbeddingGemma 300M](/da/models/embeddinggemma-300m/) %E2%80%94 Google DeepMind %C2%B7 0.3B %C2%B7 2K %C2%B7 gemma
- [EuroLLM-1.7B-Instruct](/da/models/eurollm-1-7b-instruct/) %E2%80%94 EuroLLM (utter-project) %C2%B7 1.66B %C2%B7 4K %C2%B7 apache-2.0
- [EuroLLM-22B-Instruct (2512)](/da/models/eurollm-22b-instruct-2512/) %E2%80%94 EuroLLM (utter-project) %C2%B7 22.64B %C2%B7 32K %C2%B7 apache-2.0
- [EuroLLM-9B-Instruct (2512)](/da/models/eurollm-9b-instruct-2512/) %E2%80%94 EuroLLM (utter-project) %C2%B7 9.15B %C2%B7 32K %C2%B7 apache-2.0
- [Falcon H1 1.5B Instruct](/da/models/falcon-h1-1-5b-instruct/) %E2%80%94 Technology Innovation Institute (TII) %C2%B7 other
- [Falcon H1 3B Instruct](/da/models/falcon-h1-3b-instruct/) %E2%80%94 Technology Innovation Institute (TII) %C2%B7 3.1B %C2%B7 other
- [Falcon H1 7B Instruct](/da/models/falcon-h1-7b-instruct/) %E2%80%94 Technology Innovation Institute (TII) %C2%B7 7.6B %C2%B7 other
- [Flan T5 Base](/da/models/flan-t5-base/) %E2%80%94 Google DeepMind %C2%B7 0.2B %C2%B7 apache-2.0
- [Flan T5 Small](/da/models/flan-t5-small/) %E2%80%94 Google DeepMind %C2%B7 0.1B %C2%B7 apache-2.0
- [Gemma 4 26B A4B IT](/da/models/gemma-4-26b-a4b-it/) %E2%80%94 Google DeepMind %C2%B7 25.81B %C2%B7 256K %C2%B7 apache-2.0
- [Gemma 4 31B IT](/da/models/gemma-4-31b-it/) %E2%80%94 Google DeepMind %C2%B7 31.27B %C2%B7 256K %C2%B7 apache-2.0
- [Gemma 4 E4B IT](/da/models/gemma-4-e4b-it/) %E2%80%94 Google DeepMind %C2%B7 8B %C2%B7 128K %C2%B7 apache-2.0
- [GLM-4.7-Flash](/da/models/glm-4-7-flash/) %E2%80%94 Z.ai (Zhipu AI) %C2%B7 31.22B %C2%B7 198K %C2%B7 mit
- [GLM-5.3](/da/models/glm-5-3/) %E2%80%94 Z.ai (Zhipu AI) %C2%B7 753.33B %C2%B7 1024K %C2%B7 other
- [GLM-OCR](/da/models/glm-ocr/) %E2%80%94 Z.ai (Zhipu AI) %C2%B7 1.33B %C2%B7 128K %C2%B7 mit
- [gpt-oss-120b](/da/models/gpt-oss-120b/) %E2%80%94 OpenAI %C2%B7 116.83B %C2%B7 128K %C2%B7 apache-2.0
- [gpt-oss-20b](/da/models/gpt-oss-20b/) %E2%80%94 OpenAI %C2%B7 20.91B %C2%B7 128K %C2%B7 apache-2.0
- [Granite 4.2 30B](/da/models/granite-4-2-30b/) %E2%80%94 IBM %C2%B7 29.3B %C2%B7 apache-2.0
- [Granite 4.2 3B](/da/models/granite-4-2-3b/) %E2%80%94 IBM %C2%B7 3.7B %C2%B7 apache-2.0
- [Granite 4.2 8B](/da/models/granite-4-2-8b/) %E2%80%94 IBM %C2%B7 8.8B %C2%B7 apache-2.0
- [gte-multilingual-reranker-base](/da/models/gte-multilingual-reranker-base/) %E2%80%94 Alibaba Qwen %C2%B7 0.31B %C2%B7 8K %C2%B7 apache-2.0
- [Llama 3.1 405B](/da/models/llama-3-1-405b/) %E2%80%94 Meta %C2%B7 405.9B %C2%B7 llama3.1
- [Llama 3.1 70B Instruct](/da/models/llama-3-1-70b-instruct/) %E2%80%94 Meta %C2%B7 70.6B %C2%B7 llama3.1
- [Llama 3.1 8B Instruct](/da/models/llama-3-1-8b-instruct/) %E2%80%94 Meta %C2%B7 8.03B %C2%B7 128K %C2%B7 llama3.1
- [Llama 3.2 11B Vision Instruct](/da/models/llama-3-2-11b-vision-instruct/) %E2%80%94 Meta %C2%B7 10.7B %C2%B7 llama3.2
- [Llama 3.2 1B Instruct](/da/models/llama-3-2-1b-instruct/) %E2%80%94 Meta %C2%B7 1.2B %C2%B7 llama3.2
- [Llama 3.2 3B Instruct](/da/models/llama-3-2-3b-instruct/) %E2%80%94 Meta %C2%B7 3.2B %C2%B7 llama3.2
- [Llama 3.3 70B Instruct](/da/models/llama-3-3-70b-instruct/) %E2%80%94 Meta %C2%B7 70.55B %C2%B7 128K %C2%B7 llama3.3
- [Llama 4 Maverick 17B-128E Instruct](/da/models/llama-4-maverick-17b-128e-instruct/) %E2%80%94 Meta %C2%B7 401.58B %C2%B7 1024K %C2%B7 other
- [Llama 4 Scout 17B-16E Instruct](/da/models/llama-4-scout-17b-16e-instruct/) %E2%80%94 Meta %C2%B7 108.64B %C2%B7 10240K %C2%B7 other
- [Llama Nemotron Rerank 1B v2](/da/models/llama-nemotron-rerank-1b-v2/) %E2%80%94 NVIDIA %C2%B7 1.24B %C2%B7 8K %C2%B7 other
- [Magistral Small 1.2](/da/models/magistral-small-1-2/) %E2%80%94 Mistral AI %C2%B7 24.01B %C2%B7 128K %C2%B7 apache-2.0
- [Ministral 3 8B](/da/models/ministral-3-8b/) %E2%80%94 Mistral AI %C2%B7 8.92B %C2%B7 256K %C2%B7 apache-2.0
- [Mistral 7B Instruct v0.3](/da/models/mistral-7b-instruct-v0-3/) %E2%80%94 Mistral AI %C2%B7 7.25B %C2%B7 32K %C2%B7 apache-2.0
- [Mistral Large 3 (675B)](/da/models/mistral-large-3-675b/) %E2%80%94 Mistral AI %C2%B7 675B %C2%B7 256K %C2%B7 apache-2.0
- [Mistral NeMo 12B Instruct](/da/models/mistral-nemo-12b/) %E2%80%94 Mistral AI %C2%B7 12.25B %C2%B7 128K %C2%B7 apache-2.0
- [Mistral Small 4 (119B-A6B)](/da/models/mistral-small-4-119b-a6b/) %E2%80%94 Mistral AI %C2%B7 119.4B %C2%B7 256K %C2%B7 apache-2.0
- [multilingual-e5-large](/da/models/multilingual-e5-large/) %E2%80%94 Microsoft %C2%B7 0.56B %C2%B7 1K %C2%B7 mit
- [North Micro Vision Instruct](/da/models/north-micro-vision-instruct/) %E2%80%94 Cohere %C2%B7 2.5B %C2%B7 apache-2.0
- [NVIDIA Canary 1B v2](/da/models/canary-1b-v2/) %E2%80%94 NVIDIA %C2%B7 cc-by-4.0
- [NVIDIA Nemotron 3 Embed 1B](/da/models/nemotron-3-embed-1b/) %E2%80%94 NVIDIA %C2%B7 other
- [NVIDIA Nemotron 3 Embed 8B](/da/models/nemotron-3-embed-8b/) %E2%80%94 NVIDIA %C2%B7 other
- [NVIDIA Nemotron 3 Nano 30B-A3B](/da/models/nemotron-3-nano-30b-a3b/) %E2%80%94 NVIDIA %C2%B7 31.6B %C2%B7 other
- [NVIDIA Nemotron 3 Super 120B-A12B](/da/models/nemotron-3-super-120b-a12b/) %E2%80%94 NVIDIA %C2%B7 123.61B %C2%B7 256K %C2%B7 other
- [NVIDIA Nemotron 3 Ultra 550B-A55B](/da/models/nemotron-3-ultra-550b-a55b/) %E2%80%94 NVIDIA %C2%B7 560.5B %C2%B7 other
- [NVIDIA Nemotron 3.5 Lightning 30B-A3B](/da/models/nemotron-3-5-lightning-30b-a3b/) %E2%80%94 NVIDIA %C2%B7 31.6B %C2%B7 other
- [NVIDIA Parakeet TDT 0.6B v3](/da/models/parakeet-tdt-0-6b-v3/) %E2%80%94 NVIDIA %C2%B7 cc-by-4.0
- [Pharia-1-Embedding-4608-control](/da/models/pharia-1-embedding-4608-control/) %E2%80%94 Aleph Alpha %C2%B7 7.03B %C2%B7 other
- [Pharia-1-LLM-7B-control-aligned](/da/models/pharia-1-llm-7b-control-aligned/) %E2%80%94 Aleph Alpha %C2%B7 7.04B %C2%B7 8K %C2%B7 other
- [Phi 4 Mini Instruct](/da/models/phi-4-mini-instruct/) %E2%80%94 Microsoft %C2%B7 3.8B %C2%B7 mit
- [Phi-4-multimodal-instruct](/da/models/phi-4-multimodal-instruct/) %E2%80%94 Microsoft %C2%B7 5.57B %C2%B7 128K %C2%B7 mit
- [Pixtral 12B](/da/models/pixtral-12b/) %E2%80%94 Mistral AI %C2%B7 12B %C2%B7 128K %C2%B7 apache-2.0
- [Qwen3-8B](/da/models/qwen3-8b/) %E2%80%94 Alibaba Qwen %C2%B7 8.19B %C2%B7 32K %C2%B7 apache-2.0
- [Qwen3-VL-8B-Instruct](/da/models/qwen3-vl-8b-instruct/) %E2%80%94 Alibaba Qwen %C2%B7 8.77B %C2%B7 256K %C2%B7 apache-2.0
- [Qwen3.8-27B](/da/models/qwen3-8-27b/) %E2%80%94 Alibaba Qwen %C2%B7 27.78B %C2%B7 256K %C2%B7 apache-2.0
- [Stablelm 2 1 6B](/da/models/stablelm-2-1-6b/) %E2%80%94 Stability AI %C2%B7 1.6B %C2%B7 other
- [Teuken 7B Instruct v0.6](/da/models/teuken-7b-instruct-v0-6/) %E2%80%94 OpenGPT-X (Teuken) %C2%B7 7.45B %C2%B7 4K %C2%B7 cc-by-nc-4.0
- [Voxtral Small 24B](/da/models/voxtral-small-24b/) %E2%80%94 Mistral AI %C2%B7 24.26B %C2%B7 32K %C2%B7 apache-2.0
- [Whisper Base](/da/models/whisper-base/) %E2%80%94 OpenAI %C2%B7 apache-2.0
- [Whisper Large](/da/models/whisper-large/) %E2%80%94 OpenAI %C2%B7 apache-2.0
- [Whisper Large V2](/da/models/whisper-large-v2/) %E2%80%94 OpenAI %C2%B7 apache-2.0
- [Whisper large-v3](/da/models/whisper-large-v3/) %E2%80%94 OpenAI %C2%B7 1.54B %C2%B7 apache-2.0
- [Whisper large-v3-turbo](/da/models/whisper-large-v3-turbo/) %E2%80%94 OpenAI %C2%B7 0.81B %C2%B7 mit
- [Whisper Medium](/da/models/whisper-medium/) %E2%80%94 OpenAI %C2%B7 apache-2.0
- [Whisper Small](/da/models/whisper-small/) %E2%80%94 OpenAI %C2%B7 apache-2.0
- [Whisper Tiny](/da/models/whisper-tiny/) %E2%80%94 OpenAI %C2%B7 apache-2.0

[open-weights](/da/use/open-weights/) %C2%B7[eu-builders](/da/use/eu-builders/) %C2%B7[french](/da/use/french/) %C2%B7[long-context](/da/use/long-context/) %C2%B7[coding](/da/use/coding/) %C2%B7[rag](/da/use/rag/) %C2%B7[vision](/da/use/vision/) %C2%B7[audio](/da/use/audio/) %C2%B7[apache-2](/da/use/apache-2/) %C2%B7[self-hostable](/da/use/self-hostable/) %C2%B7[catalogue-only](/da/use/catalogue-only/)