Skip to main content
Connic
Back to BlogIndustry Insights

Soofi S: What Germany's New Open Model Means for AI Agents

Germany's Soofi consortium released Soofi S, an open 30B mixture-of-experts model that leads fully open models in German and English. What it is, where it falls short, and how to run it behind production agents.

July 15, 20269 min read

On July 13, 2026, a German research consortium released Soofi S, an open 30B-parameter language model that now leads every fully open alternative on both German and English benchmarks. It is the first release from the Soofi project, a consortium coordinated by the KI Bundesverband with Fraunhofer institutes, DFKI, universities, and companies including Ellamind and Merantix Momentum. The German Federal Ministry for Economic Affairs and Energy funded the project with roughly 20 million euros. This post looks at what actually shipped, where the model is strong, where it is not, and what it takes to run it behind a production agent today.

What shipped

The release covers the base model (Soofi-S-30B-A3B on Hugging Face), an instruction-tuned preview, two reasoning previews named Isar and Rhine, intermediate training checkpoints, and the full training and evaluation code. Training ran from late March to mid May 2026 on up to 512 Nvidia B200 GPUs in Munich, about 253,000 GPU-hours on Deutsche Telekom infrastructure, over roughly 27 trillion tokens. German content was deliberately overweighted: 7.2% of the main pretraining mix and 15.3% of the later high-quality annealing phase, compared with the roughly 5% that common training recipes reserve for all non-English data combined.

31.6B
total parameters
Mixture-of-experts, 128 routed experts.
~3.2B
active per token
6 experts routed per token, plus shared experts.
1M
token context
Extended in a dedicated long-context phase.
27T
training tokens
Three phases, German overweighted throughout.

The architecture is the interesting part

Soofi S is not chasing frontier scores. It is designed to be cheap to serve. The model is a hybrid: of its 52 layers, only 6 are classic attention layers that keep a KV cache, while the rest pair Mamba-2 state-space layers with mixture-of-experts blocks. The practical consequence is that throughput barely degrades as the context grows. The consortium measured nearly constant decode speed from 4,000 out to 256,000 tokens of context: around 4,800 tokens per second per GPU at a 40,000-token context with 32 parallel requests, several times what dense models in the 14-24B range manage under the same load.

For agent workloads this is the headline feature. Agents accumulate context: system prompts, tool schemas, tool results, retrieved documents, conversation history. A model whose serving cost stays flat as that context grows is built for exactly this shape of traffic. The consortium says as much: the stated focus for the next project phase is technical documents, code generation, and agent-based systems.

Efficiency has a floor
The sparse design cuts compute per token, not memory. All 31.6B parameters have to sit in GPU memory regardless of how few are active, so the minimum hardware to serve it is that of a 30B model, even if it decodes like a much smaller one. Quantized GGUF and FP8 variants are listed as in development.

The benchmarks, honestly

Among fully open models, meaning weights, data recipe, and training code are all public, Soofi S is now the strongest on both German and English aggregates, ahead of OLMo 3 32B and Apertus 70B. Its German results are the standout: an aggregate of 79.1 and the best German code scores published for an open model. The technical report is unusually transparent about the rest.

GSM8K (math)86.1%
MBPP-DE (code, German)84.2%
German aggregate79.1%
HumanEval (code)73.8%
MBPP (code)70.2%
English aggregate70.1%
HumanEval-DE (code, German)65.5%
Minerva MATH-DE (math, German)56%
GPQA-Diamond (reasoning)43.4%

Selected scores from the Soofi S technical report, pass@1 for code benchmarks.

The caveats matter just as much. Against open-weight but not fully open models, Soofi S loses clearly: Qwen3.5 scores 74.6 on the English aggregate to Soofi's 70.1, with similar gaps on abstract reasoning benchmarks like GPQA. Competition-style math in German is weak at 56 points on Minerva MATH-DE, and open-domain factual recall runs into the limits of ~3.2B active parameters. And while long-context throughput is excellent, one RULER word-extraction subtask degrades past 32,000 tokens and drops below 5% accuracy at the longest lengths, so the 1M-token context is best treated as a throughput property, not a guarantee of reliable recall across it.

Critics have also noted that the architecture overlaps heavily with Nvidia's Nemotron 3 Nano family and argue that continual pretraining on an existing base would have cost far less than the 253,000 GPU-hours spent. That is a fair critique of the economics. It does not change what the released artifact is: a fully reproducible, German-strong open model that anyone can inspect, retrain, or build on.

What open means here

Soofi S meets the Open Source AI Definition 1.0 from the Open Source Initiative. About 99% of the training run can be independently reconstructed from the published data accounting; the remainder is commercially licensed German newspaper archive content that cannot be redistributed. Weights, intermediate checkpoints, training code, and evaluation code are all public, which puts it in a small club alongside OLMo and Apertus rather than the much larger group of weights-only releases.

Check the license before you build
At release the Hugging Face model card listed a custom license whose full text was still pending. Until the final text lands, treat any production or commercial plan as provisional. This is the single most important thing to re-check before committing to the model.

Running Soofi S behind an agent

Because Connic is bring-your-own-key and never hosts models itself, an open model you serve yourself plugs in the same way any provider does. Serve Soofi S with vLLM or, once the quantized variants land, llama.cpp or Ollama, register the endpoint as a custom OpenAI-compatible provider in your project settings, and reference it from the agent config:

Same agent, your endpoint
A custom provider gets a model prefix, so switching an agent from a commercial model to your own Soofi S deployment is a one-line change, for example model: vllm/soofi-s-instruct. If the inference box lives inside your private network, agents reach it through the bridge instead of the public internet. Guardrails, judges, traces, and approvals work the same regardless of which model answers.

The honest caveats carry through. The base model is explicitly not meant for direct use without post-training, the instruct and reasoning variants are previews, and there is no commercial support behind the project: patches, security updates, and incident response are yours. That is the standard trade of self-hosting, and it is why we would put Soofi S on a slice of real traffic behind an A/B test, with judges scoring its output, before routing anything important to it. Our DACH report found 23% of production agents in the region already run open-weight or self-hosted models, so the operational pattern is well established; what has been missing is a German-first model worth the effort.

Run open models behind production agents

Connect a self-hosted Soofi S endpoint as a custom provider and put guardrails, judges, and traces around it, alongside whichever commercial models you already use.

Get started free

The sovereignty question

Soofi S will be discussed mostly in sovereignty terms, and it is worth being precise about what it does and does not settle. It does not make the strongest closed or open-weight models redundant; the benchmark gaps are real. What it does provide is something that did not exist before: a competitive, fully reproducible model that is strong in German, trained in the EU, and able to run entirely on infrastructure you control. For teams whose deployments hinge on EU AI Act readiness and keeping data inside the EU, that combination is the point, independent of leaderboard positions.

Three things to watch from here: the final license text, the instruct model graduating from preview, and the consortium's next phase, which targets agent systems directly and is looking for industry partners. If those land, the default answer to "which model do we self-host for German workloads" is about to change.

Frequently Asked Questions

What is Soofi S?

Soofi S is a fully open 30B-parameter mixture-of-experts language model released on July 13, 2026 by a German research consortium coordinated by the KI Bundesverband, with participants including Fraunhofer institutes, DFKI, universities, and companies such as Ellamind and Merantix Momentum. It activates about 3.2B parameters per token, supports contexts up to 1 million tokens, and focuses on German and English.

Is Soofi S open source?

It meets the Open Source AI Definition 1.0: weights, intermediate checkpoints, training code, evaluation code, and per-source data accounting are all public, and about 99% of training can be independently reconstructed. However, the full text of its custom license was still pending at release, so commercial plans should wait for the final license.

How good is Soofi S compared to other models?

Among fully open models it leads both German and English aggregate benchmarks, ahead of OLMo 3 32B and Apertus 70B, with especially strong German code results. Against open-weight models like Qwen3.5 it trails on English and abstract reasoning. Weak spots include German competition math, open-domain factual recall, and reliable recall over very long contexts.

Why is Soofi S efficient to serve?

It uses a hybrid architecture: only 6 of 52 layers are attention layers that keep a KV cache, and the rest combine Mamba-2 state-space layers with mixture-of-experts blocks. Decode throughput stays nearly constant from 4,000 to 256,000 tokens of context. The trade-off is memory: all 31.6B parameters must be loaded even though few are active per token.

Can I run AI agents on Soofi S?

Yes, with caveats. You serve the model yourself, for example with vLLM, and connect the endpoint to an agent platform as an OpenAI-compatible provider. On Connic this is a custom provider in project settings, and a private inference endpoint can be reached through the bridge. The instruct and reasoning variants were still previews at release, so evaluate on real traffic before routing important workloads to it.

What hardware does Soofi S need?

The unquantized model ships as bf16 safetensors and requires enough GPU memory to hold all 31.6B parameters, on Nvidia Ampere-generation GPUs or newer. Quantized GGUF and FP8 variants for smaller setups were listed as in development at release.

Why does Soofi S matter for EU and German companies?

It is a competitive model that is strong in German, fully reproducible, trained in the EU, and able to run entirely on self-controlled infrastructure. For teams whose deployments depend on EU data residency and EU AI Act readiness, that combination matters independent of whether it tops global leaderboards.

More from the Blog

Industry Insights

What Is an MCP Connector? A Practical Definition

An MCP connector links an AI app to external tools and data over the Model Context Protocol. Learn how it works and when it beats a custom API integration.

July 8, 20268 min read
Industry Insights

AI Agent Platforms With EU Data Residency: 2026 Shortlist

Which AI agent platforms keep data in the EU? The 2026 shortlist grouped by residency model, and what residency must cover: traces, storage, model calls.

July 6, 202612 min read
Industry Insights

State of AI Agents in DACH 2026

How DACH teams build, trigger, and run production AI agents in 2026 — adoption, model mix, connectors, cost, reliability, and compliance, from Connic customer data.

June 27, 202612 min read
Industry Insights

Pre-built Connectors for AI Agents: Skip the Integration Glue

Production agents have to receive events from and send results to the systems around them. Pre-built connectors turn that plumbing into a platform feature instead of custom code you write and maintain.

June 16, 20268 min read
Industry Insights

The Real Cost of Assembling Your Own AI Agent Stack

The real cost of assembling your own AI agent stack isn't the tools — it's the integration and maintenance tax between them, and when buying a platform wins.

June 9, 202610 min read
Industry Insights

How to Run AI Agents in the EU Without US Hyperscalers

Run production AI agents in the EU without US hyperscalers: what EU-hosted must really mean, where the US CLOUD Act exposes you, and a sovereignty checklist.

June 4, 20269 min read
Industry Insights

Managed vs Self-Hosted AI Agents: TCO at 50,000 Runs/Month

A line-item TCO model at 50,000 AI agent runs/month, comparing self-hosted Kubernetes, Connic Pro (subscription-as-credit with uniform per-unit rates), and Inngest. EUR throughout, with cited sources.

May 16, 202613 min read
Industry Insights

AI Agent Deployment Platforms in 2026: 4 Types Compared

Agent-native runtimes, workflow engines, framework stacks, or plain frameworks? Compare the 4 platform types on lock-in, pricing, and connectors.

April 19, 202612 min read
Industry Insights

The EU AI Act Is Here. Your AI Agents Need to Comply.

The EU AI Act is the world's first comprehensive AI regulation, and it applies to your AI agents today. Here's what it requires, what the penalties look like, and how Connic makes compliance the default rather than an afterthought.

April 13, 202611 min read