Sovereign Devices
Private AI hardware. Your data never leaves.
GB10-class sovereign AI machines, available in ASUS and Dell variants, sold and provisioned by us. A single unit runs models up to ~200B parameters (quantized); stack units to serve larger models and your whole company.
Official manufacturer product images — ASUS Ascent GX10 and Dell Pro Max with GB10.
What fits on one unit — and on two: the on-premises model catalog →
One unit runs big models
Our devices are GB10-class machines — NVIDIA DGX Spark-class systems with 128 GB of unified memory, compact enough for an office. A single unit serves open-weight models up to roughly 200B parameters (quantized) entirely locally.
We operate this exact hardware ourselves, daily, as the inference fleet behind our own products. What we sell is the setup we run.
- Available in ASUS and Dell variants — same GB10-class platform, your choice of manufacturer.
- Sold and provisioned by BrainOutput: delivered with a working model stack, not an empty box.
- Runs private LLM inference locally — prompts, documents, and outputs stay on the machine.
Stack units to cover your whole company
When one unit is not enough, units stack: interconnected devices serve larger models and handle an entire company's AI workload. We run our own production models across stacked units — the scaling path we sell is the one we use.
- Stack units to serve models larger than a single machine can hold.
- Scale capacity as your team's usage grows — add units, keep everything on-premise.
- Pricing and configurations: sur devis — request an assessment and we scope the right sovereign setup for you.
Models that fit — including Europe's best
A single unit (128 GB unified memory) comfortably serves European flagship models — Mistral Large-class models (~120B parameters, quantized) run on one device, entirely under your control. European models on European-controlled hardware is the cleanest sovereignty story there is.
We publish what we run: Qwen3.5-122B serves on a single unit in our own fleet, and our company's planning and coding brain — DeepSeek-V4-Flash, a 284B-parameter mixture-of-experts model — runs in production across two stacked units. These are measured deployments, not datasheet promises.
- One unit: Mistral Large-class (~120B quantized), Qwen3.5-122B-class, and every smaller open-weight model — coding, chat, embedding.
- Two stacked units: ~300B-class mixture-of-experts models (our own production configuration) with headroom toward ~400B-class quantized.
- Mistral and the growing European open-weight ecosystem, first-class: EU models, EU hardware, EU data residency.
What companies run on them
Sovereign AI is what businesses search for when the cloud stops being an option. These machines answer the use cases behind that search:
- Private document analysis and retrieval (RAG) — contracts, dossiers, and archives queried on-premise.
- On-premises AI assistants and agent teams for regulated professions — GDPR and EU AI Act aligned by construction.
- Fine-tuned vertical models from our LLM Factory, delivered onto your device and kept current.
- Private coding assistants for your engineering team — your source code never leaves the building.
- Customer service and back-office automation on your own hardware, in your own language.
Why sovereign hardware
For regulated professions and privacy-critical businesses, the simplest compliance story is physical: the model runs in your office, and your data never leaves it. No cloud API, no third-party processor, no data transfer to reason about.
Our devices, deployments, and operating processes are designed with ISO/IEC 42001 AI management principles in mind — risk management, accountability, and lifecycle governance built into how we provision and maintain every machine.