A Sovereign, Open-Source Foundation Model for German and English
We present Soofi S 30B-A3B, a sovereign, open-source Mixture-of-Experts (MoE) hybrid Mamba Transformer foundation model for German and English. Its hybrid design activates only 3B of 30B parameters per token and keeps the inference cache near-constant as context grows, giving it a decisive throughput advantage over dense models for long-context, high-concurrency deployment. Pretrained on roughly 27 trillion tokens with deliberately up-weighted German, Soofi S matches dense 14 to 27B models on aggregate English and German benchmarks while achieving the best code aggregates in both languages amo
Lineage graph
Paper → model → repo connections mined from source citations (Tier-1 exact match).
Why these links exist
Every edge carries a method, confidence, and the source snippet that justified it — so bad links are debuggable.
- PossiblePossibly related (embedding) · 58%thu-pacman/chitu →
- PossiblePossibly related (embedding) · 58%lone-cloud/gerbil →
- PossiblePossibly related (embedding) · 57%chrisliu298/awesome-llm-unlearning →
- PossiblePossibly related (embedding) · 56%EuroEval/EuroEval →
- PossiblePossibly related (embedding) · 56%Atomic-man007/Awesome_Multimodel_LLM →
- PossiblePossibly related (embedding) · 50%Xiaohao-Liu/Awesome-Multi-Token-Prediction →
- PossiblePossibly related (embedding) · 45%Large language models could democratize data use—but only if the foundations are in place - World Bank Blogs →
- PossiblePossibly related (embedding) · 57%German AI consortium releases Soofi S, an open 30B model that tops benchmarks in both English and German - the-decoder.com →
