Soofi Consortium Releases Soofi S 30B-A3B: An Open Hybrid Mamba-Transformer MoE Foundation Model For German And English


A German research consortium has published the pretraining report for Soofi S 30B-A3B. It is an open base model for German and English. Training ran end to end on Deutsche Telekom’s Industrial AI Cloud in Munich. Preview weights are on Hugging Face. It is worth noting that among some of the fully open base models tested, Soofi S records the highest English and German aggregate scores.

What is Soofi S 30B-A3B?

Soofi S is a Mixture-of-Experts (MoE) hybrid Mamba Transformer foundation model. It totals ~31.6B parameters and activates ~3.2B per token. As a base model, it has no instruction tuning, alignment, or safety tuning. The KI Bundesverband coordinates the consortium, funded by the German Federal Ministry for Economic Affairs and Energy. Participants include Fraunhofer IAIS, DFKI, TU Darmstadt, ellamind, and Merantix Momentum.

How the architecture works?

The efficiency claim starts with the layer stack. The network holds 52 layers. That is 23 Mamba-2 sequence-mixing layers, 23 granular MoE layers, and 6 Grouped-Query Attention (GQA) layers. Only those 6 GQA layers maintain a KV cache. Each MoE layer holds 128 routed experts, activates 6 per token, and adds 2 shared experts. Other details: model dimension 2688, squared ReLU, RMSNorm, and no positional embeddings.

Soofi S adopts the Nemotron 3 Nano reference design without modification. The research team gives three reasons for that choice. Those are deployability on stacks such as vLLM, serving efficiency, and scientific control. Because the backbone is fixed, Nemotron 3 Nano becomes an architecture-identical baseline. The data recipe is the only moving part.



Source link

  • Related Posts

    Building a Gin Config Controlled PyTorch Pipeline with Configurable MLP Variants, Cosine Scheduling, and Runtime Parameter Overrides

    In this tutorial, we implement a Gin Config–controlled PyTorch experiment pipeline in which the executable training code remains stable. At the same time, the experimental degrees of freedom are moved…

    Google Releases LiteRT.js: A JavaScript Binding of LiteRT That Runs .tflite Models in Browsers via WebGPU

    Google released LiteRT.js, a JavaScript binding of LiteRT. LiteRT is Google’s on-device inference library, previously called TensorFlow Lite. LiteRT.js runs .tflite models directly inside the browser. Because inference stays local,…

    Leave a Reply

    Your email address will not be published. Required fields are marked *