BrainOutput
English

Runs on a private AI box you own

One compact GB10-class device — 128 GB unified memory — runs it on-premise, sold and provisioned by us. No cloud API keys, no data leaving the building.

ASUS Ascent GX10 — GB10-class sovereign AI device on a desk (official ASUS image)
ASUS Ascent GX10from €3 650,22 HT
Dell Pro Max with GB10 — GB10-class sovereign AI device (official Dell image)
Dell Pro Max with GB10from €4 328,25 HT

All on-premises model pages

Run Llama 4 Scout on-premises

Memory-fit arithmetic — checkable math, not a deployment claim

Llama 4 Scout is Meta's compact Llama 4 variant: 109 billion total parameters with 17 billion active (16 experts), natively multimodal and advertised with a very long context window. It fits a single GB10-class unit at 4-bit with room for context.

Here is the arithmetic on a 128 GB unit.

Memory fit on a 128 GB unit

Parameters109B total, 17B active (16 experts, MoE)
4-bit weights~55–60 GB
Device memory128 GB unified (one unit)
Left for context cache + systemroughly 50 GB
Units required1

At 4-bit Scout fits one unit; its long advertised context is bounded in practice by the KV-cache memory you leave free, which we size in the assessment.

What it serves well

  • Multimodal workloads (text + images) served entirely on-premise.
  • Long-document tasks where a large context window helps.
  • Teams standardizing on the Llama ecosystem and tooling.

Honest limits

  • Arithmetic, not our measured deployment. The memory envelope is smaller than models we run measured on this hardware.
  • Llama 4 ships under Meta's Llama 4 Community License, which carries use restrictions (including a large-user clause). We review licensing fit as part of the assessment.
  • The bigger Llama 4 Maverick (~400B) does NOT fit one box — it needs multiple stacked units or is out of scope.

Frequently asked questions

Does Llama 4 Scout fit one unit?
Yes, at 4-bit: ~55–60 GB of weights against 128 GB, leaving roughly 50 GB for context and system.
Is the license fully open?
No — it is the Llama 4 Community License with use restrictions, not a plain OSI license. We flag this rather than imply otherwise.
What about Llama 4 Maverick?
Maverick (~400B) does not fit a single 128 GB unit; it would require multiple stacked units. We say so plainly.
Request an assessment & quoteThe machine this math is about — Sovereign DevicesFine-tune a model on your data — LLM Factory