Answers with sources
Every answer shows where it came from.
Ask a question and get an answer drawn from your own files, with the source documents linked.
Private RAG: ask your own documents with private AI
Unlock the potential of your own data. Search, question and summarise your documents, with answers that show their sources, without anything leaving the building. Renderboxes can help you put powerful local AI compute to work.
The possibilities with private, local AI
Contracts and policies
Find the clause, compare the versions.
Search contracts, policies and terms in plain English, without uploading them anywhere.
Manuals and knowledge bases
Your team’s know-how, on tap.
Turn manuals, procedures and project archives into a knowledge base anyone can question.
Project files and briefs
Pick up any project quickly.
Summarise briefs, feedback and project history so people get up to speed fast.
New documents, added automatically
Keep the knowledge base current.
New files can be indexed as they arrive, without slowing down everyone else.
Confidential stays confidential
Built for sensitive material.
Client work, HR files and finance documents stay on hardware you own, with access you control.
Local AI capabilities, model support and performance vary by model, configuration, software and workload.
Protect your business
We can help you build AI workflows that protect your business.
- Help keep your data secure. Prompts, documents and answers are processed on your own hardware, on your own network. Nothing is retained by an AI provider and nothing trains someone else’s model.
- Your identity, protected. Personal and confidential details can be masked automatically at every exit, so only what is safe to send ever leaves the building.
- A record you own. Every request and action can be logged to a tamper-evident audit trail on your own disks, which helps you meet client confidentiality and GDPR obligations.
Reduce token costs
PREDICTABLE COSTS FOR THE WHOLE TEAM
Replace per-seat AI subscriptions and usage-based token fees with a fixed cost for on-premises compute your whole team can share. Workflows can be set up to check your own knowledge before a paid cloud call, and any cloud use can be capped, with a kill switch that you control.
Ready on day one: RBOS and RBOS Studio
Skip the weeks of set-up. RBOS and RBOS Studio can come preloaded, configured and tested together, so your team starts on the work, not the software.
- One-click workflows. Runbooks set up team chat, document search, coding assistants, transcription and model serving with step-by-step guidance.
- Your team gets simple, IT keeps control. Everyone works in a browser on your network, while admins decide who can use what and every action is logged.
- Change it as your work changes. Add or remove workflows at any time, with no endless tweaking.
- See every GPU at work. Assign workflows to GPUs and see what each one is doing.
Works with the software you use
We can set up, test and support popular AI software on your machine before it ships, including:
Open WebUI · Ollama · llama.cpp · vLLM · PostgreSQL with pgvector
Using something else? Tell us and we will help you make it work.
AMD or NVIDIA: your choice
We build private AI systems on AMD Radeon AI PRO and NVIDIA RTX PRO Blackwell GPUs, and RBOS sets up either, or both in one machine.
- AMD Radeon AI PRO. More GPUs for the money: run several everyday models side by side, one per GPU, for a team.
- NVIDIA RTX PRO 6000 Blackwell. 3× the VRAM per GPU, for flagship open models, the longest documents and more people at once.
- Not sure? Tell us what your team wants to do and we will recommend the right mix.
Recommended builds
Documents – Standard (AMD, budget)
Photon · AMD Radeon AI PRO R9700 32GB
32GB VRAM, for one person getting started.
- CPU: AMD Ryzen 9 9950X3D
- RAM: 64GB UDIMM ECC DDR5 5600Mhz
- PCIe Slot: AMD Radeon AI PRO R9700 32GB
- NVMe Storage (Gen 5.0): Samsung 9100 Pro Gen 5 2TB
- Operating System: RBOS Ubuntu LTS
£5,308.62 inc VAT
£4,423.85 ex VAT
Built to order · dispatched in 3 working days
Documents – Heavy
Photon · NVIDIA RTX PRO 6000 Blackwell Max-Q 96GB
96GB VRAM, for one person working with the largest models.
- CPU: AMD Ryzen 9 9950X3D
- RAM: 128GB DDR5 6000 2x64GB
- PCIe Slot: Nvidia RTX Pro 6000 Blackwell Max-Q 96GB
- NVMe Storage (Gen 5.0): Samsung 9100 Pro Gen 5 4TB
- Operating System: Microsoft Windows 11 Pro
£22,577.13 inc VAT
£18,814.28 ex VAT
Built to order · dispatched in 10 working days
Documents – Studio
Atom · 2x NVIDIA RTX PRO 6000 Max-Q 96GB
192GB VRAM across 2 GPUs, for a small team.
- CPU: AMD Ryzen Threadripper 9970X 32 Core
- RAM: 4 × 128GB RDIMM ECC DDR5 6400
- PCIe slots (16x): 2 × Nvidia RTX Pro 6000 Blackwell Max-Q 96GB
- NVMe M.2 Drives (Gen 5): Samsung 9100 Pro Gen 5 2TB
- NVMe M.2 Drives (Gen 5): Samsung 9100 Pro Gen 5 8TB
- Operating System: RBOS Ubuntu LTS
£68,450.43 inc VAT
£57,042.04 ex VAT
Built to order · dispatched in 11 working days
Documents – Team
Nano Pro · 4x NVIDIA RTX PRO 6000 Max-Q 96GB
384GB VRAM across 4 GPUs, for the whole team.
- CPU: AMD Ryzen Threadripper PRO 9975WX 32 Core
- RAM: 8 × 128GB RDIMM ECC DDR5 6400
- PCIe Options: 4 × Nvidia RTX Pro 6000 Blackwell Max-Q 96GB
- NVMe M.2 Drives (Gen 5): Samsung 9100 Pro Gen 5 2TB
- U.2 Drives: 2 × Micron 9550P 15.36TB U.2 NVMe
- Operating System: RBOS Ubuntu LTS
£144,186.60 inc VAT
£120,155.54 ex VAT
Built to order · dispatched in 12 working days
Each recommended system is a starting point. Select Customise to add components or change the specification before you order.
Inside the Atom
- Two GPUs in a desk-side chassis on castors.
- AMD Ryzen Threadripper and up to 1 TB of ECC memory.
- Cooling engineered for sustained AI work, all day.
The machine underneath
- 1In the largest build here, with NVIDIA RTX PRO 6000 Blackwell GPUs. Total VRAM depends on the GPUs specified.
- 2Plus 1-year return-to-base labour and 3 years of technical support.
Scale up as your team grows
2-GPU private AI
The Atom: 2× the GPUs and VRAM of a Photon3, for a team getting started with private AI.
Explore
4-GPU private AI
The Nano Pro: 4× a Photon, desk-side, for heavier models and more people at once.
Explore
8-GPU AI compute node
The Molecule Air: 8× a Photon, for whole-company AI, agents and fine-tuning.
Explore
- 3Compared with a single-GPU Photon fitted with the same GPU, counting GPUs and total VRAM. Real-world performance varies by model, configuration, software and workload.
Why Renderboxes
- Engineered for demanding AI work. Built and stress-tested in the UK for generative AI, agents, document search and fine-tuning, running all day.
- Software ready. RBOS and RBOS Studio prepared for your AI work before delivery.
- Secure and reliable. Your models and data on hardware you own, supported by the people who built it.
- Future-proofed. Upgrade GPUs, memory and storage as your work grows, or move up to four or eight GPUs.
Frequently asked questions
PDFs, Word and text files, spreadsheets, presentations and more. We can help you connect your own document stores and decide who can see what.
No. RBOS Studio runs in a browser, and Runbooks guide you through set-up step by step. We can also set the machine up for your workflows before it ships.
Not unless you choose to. Everyday work runs on the machine. If you use a cloud model for harder tasks, personal and confidential details can be masked before anything is sent.
It can. You could keep the machine for private and everyday work and use a cloud model only for the hardest tasks, with spending capped. We can help you set that up.
That depends on your workflows and how heavily they are used. Tell us about your team and we will size the machine for it.
AMD gives you more GPUs for the money and suits several everyday models running at once. NVIDIA gives the most VRAM per card, for flagship models and the longest documents.
Yes. We keep developing new workflows, and if you need one we do not list, talk to us and we will help you make it work.
Yes. Select Customise and the configurator opens with this build already selected.
Tell us what you’d like your team to do with private AI
Tell us the kinds of documents you want to search, roughly how many there are, how many people will use it and any data-handling rules, and we will recommend the right build.
Talk to someone at Renderboxes
Not sure which build is right? Speak to our team and we will help you choose the right configuration for your work.
Send us an enquiry
Tell us what you are working on and we will recommend a configuration.
Contact us