Family owned & operated Based in Florida, USA

Affordable GPU Supercomputers
for Offline, Private AI.

Norman Supercomputers, Inc. designs and builds on-prem, air-gapped GPU supercomputers for hobbyists, extreme gamers, tech enthusiasts, businesses, and startups who need serious AI performance without surrendering their data to the cloud.

70B+ parameter LLMs locally Stable Diffusion XL & video generation Fully private, no subscriptions ECC RAM for long training runs
Join the early access list

All initial systems are in design and validation. Models & pricing: TO BE ANNOUNCED.
Join the mailing list to be the first to hear when pre-orders open.

Concept Design
RTX 5090 Series

NS-Series GPU Supercomputer

Our reference designs are tuned around next-generation RTX 50-series GPUs, ECC memory, and high-core Threadripper & Ryzen CPUs, all configured for 24/7 offline AI workloads.

Target VRAM
64–192 GB
GPU Count
2–6 GPUs
CPU
Ryzen / Threadripper
OS
Ubuntu 24.04 LTS

Ollama ComfyUI Axolotl fine-tuning 100% offline

As a Florida-based family business, we build and test each system as if we were putting it in our own home lab. No mystery parts, no aggressive upselling — just honest, high-performance machines tuned for real-world AI workloads.

NS-Series Supercomputers

Three tiers of local AI power. All models and pricing are currently TO BE ANNOUNCED, but these are the design targets we’re working toward.

Design reference only – subject to change
Entry AI Lab To Be Announced

NS-64 Pioneer

Designed as an “AI starter” supercomputer for hobbyists, small teams, and serious gamers who want to run large models locally without breaking the bank.

  • Target GPUs: 2× RTX 5090 (≈ 64 GB total VRAM)
  • CPU: Ryzen 9 7950X3D (16 cores)
  • Memory: 128 GB DDR5 ECC
  • Storage: 4–8 TB NVMe SSD (AI-ready)
  • Power: ~1,400W, air-cooled

Internal testing target: ~40–50 tokens/sec on a 70B LLM (fp16), and smooth Stable Diffusion XL image generation at 2–3 it/s.

Home lab Solo founder Advanced gamer
Sweet-spot Workhorse To Be Announced

NS-128 Vanguard

Our “best value” concept: a balanced, multi-GPU system for small businesses and AI-heavy startups that need serious throughput without going into datacenter pricing.

  • Target GPUs: 4× RTX 5090 (≈ 128 GB total VRAM)
  • CPU: Threadripper PRO 7955WX (16 cores)
  • Memory: 256 GB DDR5 ECC
  • Storage: 8–16 TB NVMe SSD (RAID options)
  • Power: ~2,400W, tuned air-cooling

Internal goal: ~75–85 tokens/sec on a 70B LLM (fp16), 4.5–5.5 it/s on SDXL, and practical fine-tuning for 13B models in 4–5 hours.

Startup AI stack In-house R&D Small studio render
High-end Local Cluster To Be Announced

NS-192 Titan

A concept “AI beast” for teams that want a serious local alternative to rented cloud clusters, with room to push bigger models and heavier fine-tunes.

  • Target GPUs: 6× RTX 5090 (≈ 192 GB total VRAM)
  • CPU: Threadripper PRO 7960X (24 cores)
  • Memory: 512 GB DDR5 ECC
  • Storage: 16–24 TB NVMe SSD (RAID / scratch)
  • Power: ~3,600W, custom loop cooling

Design target: ~100–110 tokens/sec on 70B LLMs (fp16), 6.5–7.5 it/s SDXL, and 13B fine-tunes in around 3–3.5 hours.

Research lab Enterprise pilot Multi-user cluster

All specifications and names are preliminary and may change. Final model names, prices, and configurations are TO BE ANNOUNCED.

Why on-prem, offline AI?

Cloud GPUs are great — until you factor in privacy, latency, and surprise bills. Norman Supercomputers exist so you can keep your data and your compute under one roof.

1

Data stays in your building

Fine-tune models on proprietary code, medical records, financial data, or any sensitive information without sending a single token to a third-party cloud.

2

Predictable cost, no “surge pricing”

Once your system is paid for, the only ongoing cost is power and maintenance. No more watching usage dashboards to avoid surprise multi-thousand-dollar bills.

3

Instant experimentation

Spin up local LLMs, diffusion models, and fine-tunes as quickly as you can type a command. No queueing, rate limiting, or waiting for capacity.

4

Family-owned accountability

You’re not a ticket number. When something matters, you can talk to the people who actually design and build these systems — not just a reseller.

Core software stack (planned)

100% Offline by default

Every Norman Supercomputer is designed to ship with a curated, local-first AI toolkit:

  • Ubuntu 24.04 LTS + NVIDIA CUDA 12.6, tuned for multi-GPU workloads.
  • Ollama for local LLMs (chat, coding, embeddings), pre-configured with popular open models.
  • ComfyUI for Stable Diffusion XL and image/video workflows.
  • Axolotl and supporting tools for fine-tuning 7B–70B class models.
  • ECC RAM configurations for long-running training jobs.
  • No cloud accounts required; everything can run completely disconnected.

Software selections are also evolving and may be tailored per customer at launch.

Design targets & performance envelope

Below is the internal reference table we’re using to shape the NS-Series. These numbers are based on our current component assumptions and are for planning only; final systems will be benchmarked and documented at launch.

Metric NS-64 Pioneer NS-128 Vanguard NS-192 Titan PewDiePie-style Lab*
Total VRAM 64 GB 128 GB 192 GB ~424 GB
70B LLM (fp16) inference 40–50 tokens/sec 75–85 tokens/sec 100–110 tokens/sec ~120–140 tokens/sec
Fine-tune 13B model 6–8 hours 4–5 hours 3–3.5 hours 2–3 hours
Stable Diffusion XL 2–3 it/s 4.5–5.5 it/s 6.5–7.5 it/s 8–10 it/s
Power draw (full load) ~1,400W ~2,400W ~3,600W ~3,500W
Est. monthly electric (24/7) ≈ $100 ≈ $200 ≈ $300 ≈ $500+
Noise level 40–45 dB 45–50 dB 55–60 dB 65–70 dB

*“PewDiePie-style lab” refers to a roughly comparable 10-GPU enthusiast build (8× modded 4090 + 2× 4000 Ada). It’s included here only as a reference point for extreme community builds and is not a product we sell.

Diminishing returns snapshot:
  • $5K → $10K class: +100% cost → +80–100% performance (sweet spot).
  • $10K → $20K class: +100% cost → +25–30% performance (diminishing returns).
  • Above $20K: steep cost for marginal gains, mostly edge-case laboratories.
Design philosophy:
  • 128 GB VRAM covers ~95% of real-world local AI use cases.
  • Extra VRAM mainly helps for very large, less quantized models and exotic experiments.

Join our mailing list

Get notified when Norman Supercomputers become available, including model reveals, pricing, and early-access opportunities. Opt-out anytime.

We do not sell or share your info. Used only for updates about Norman Supercomputers. Opt-out anytime. See .

Privacy Policy (mailing list)

1. Purpose of collection
We collect your email address (and optional name / interest information) solely for the purpose of sending you updates about Norman Supercomputers, including:

  • Announcements about product availability and pre-orders.
  • Specs and pricing updates as our models are finalized.
  • Important changes to our offerings or policies.

2. No sale or third-party sharing
We do not sell, rent, or trade your contact information with any third parties. We also do not share your email address or other details with marketing lists, brokers, or advertisers.

3. Opt-out anytime
Every email we send will include a simple unsubscribe link. Clicking that link will remove you from our mailing list. You may also contact us directly to request removal.

4. Data retention
We retain your mailing list information only as long as it is needed for the purposes described above or until you unsubscribe.

5. Security
We use reasonable technical and organizational measures to keep your contact information secure and separate from any production systems.

As a small, family-run company, we take your trust seriously. If you ever have questions or concerns about how your information is used, please reach out and we’ll address it directly.

This policy applies specifically to our mailing list. A fuller site-wide privacy policy will be published alongside our product launch.