NGARi+ is the hardware line. A NVIDIA Jetson at the centre, the sovereign stack on top, and nothing leaving the box. The model runs here. The agents run here. Your data stays here — because there is nowhere else for it to go.
Ships pre-flashed and configured · typically 7–14 business days · 2-year hardware warranty · 30-day returns after delivery · installment plans available
67 → 2070TOPS across the line
0 bytestransmitted — verified on device
6 agentspre-installed, ready on day one
$0per token, forever
The line
Three machines, one principle: the intelligence is yours. Pick by the largest model you need to run and how many agents you need working at once.
Illustration
Illustration. NGARi+ Nano is built on the NVIDIA Jetson Orin Nano class module and is the only model in the line that ships in a NGARi-designed enclosure. Shown as a drawing pending production photography.
Entry
NGARi+ Nano
The one that fits in a drawer and replaces a subscription.
$999 one-time
67 TOPS · NVIDIA Jetson Orin Nano class
8 GB unified memory · 512 GB NVMe
Runs 7B–14B models comfortably
6 agents included · palm-sized · ~25 W
Installments: 2 × $499.50 or 4 × $249.75 — 0% interest; the payments total the same $999.00. How plans work
Photo: the NVIDIA Jetson AGX Orin Developer Kit — the enclosure NGARi+ Orin ships in, pre-installed and verified with the sovereign stack. Orin and Thor ship in NVIDIA’s own enclosures; NGARi+ Nano is the one model with a NGARi-designed enclosure.
Most popular
NGARi+ Orin
The one that runs the big model and the whole C-suite.
$4,999 one-time
275 TOPS · NVIDIA Jetson AGX Orin 64 GB
64 GB unified memory · 1 TB NVMe
All models incl. 32B class, including qwen3.8
All six agents concurrent, plus your own · 15–60 W
Installments: 2 × $2,499.50 or 4 × $1,249.75 — 0% interest; the payments total the same $4,999.00. How plans work
Illustration. NGARi+ Thor is built on the NVIDIA Jetson AGX Thor module and ships in NVIDIA’s own AGX Thor enclosure. No licensed photograph of it is available yet, so this is a drawing rather than a photo.
Frontier
NGARi+ Thor
The one that trains, sees, and drives machines.
$8,999 one-time
Up to 2,070 TFLOPS · Jetson AGX Thor, Blackwell
128 GB unified memory · 2 TB NVMe
Runs 70B–100B+ quantized, multimodal, vision
Unlimited agents · robotics-grade · 40–130 W
Installments: 2 × $4,499.50 or 4 × $2,249.75 — 0% interest; the payments total the same $8,999.00. How plans work
This is not a faster chatbot. It is a machine that removes three bills, one dependency, and one ceiling at the same time.
Your C-suite, on your desk
Six autonomous executives — CEO, CRO, Engineer, Worker, CMO, Chief of Staff — running continuously on hardware you own, with hash-chained audit records of everything they do.
An air-gapped second brain
Ingest contracts, records, research and client files, then search and reason over them with zero outbound traffic. The answer never leaves the room.
Fine-tune on your own data
Train the model on what makes your business yours. No data-licensing clause, no upload, no one else's terms of service. The weights live on your NVMe.
Works when the internet doesn't
Denied, degraded, intermittent, low-bandwidth. Ships, clinics, farms, field teams, basements, borders. Inference does not stop when the link does.
No per-token bill, ever
Your 10,000th question costs the same as your first: nothing. Usage cannot be metered against you because usage is not observable by anyone but you.
A skill you can teach
Standardise how your team uses AI — one box, one stack, one governance model — then certify people on it through AI-Corps.
The math that sells itself
A rented model is a subscription that never ends and never becomes an asset. At a blended frontier-cloud price of roughly $15 per 1M tokens, a team using 50M tokens a month spends $750 every month — $27,000 over three years. NGARi+ Orin is $4,999, once, and it is still yours in year four.
Frontier cloud · 3 yr
$27,000
NGARi+ Thor · once
$8,999
NGARi+ Orin · once
$4,999
NGARi API · 3 yr
$3,600
NGARi+ Nano · once
$999
At that volume, NGARi+ Nano pays for itself in about six weeks and Orin in about seven months — and unlike the cloud bill, the asset never resets to zero.
Illustrative. The frontier-cloud figure assumes a blended $15 per 1M tokens at 50M tokens per month; the NGARi API figure uses our published $2.00 per 1M tokens at the same volume. Third-party pricing varies widely by model and provider and is often higher. NGARi+ carries no recurring fee.
What fits on each machine
Nano · 67 TOPS
7B–14B
Orin · 275 TOPS
up to 32B
Thor · 2,070 TFLOPS
70B–100B+
Comfortable quantized model range. Smaller models always run faster; larger models fit on Thor with reduced context. Vision and multimodal run on Orin and Thor.
Full specifications
Specification
NGARi+ Nano
NGARi+ Orin
NGARi+ Thor
Price
$999 one-time
$4,999 one-time
$8,999 one-time
Accelerator
NVIDIA Jetson Orin Nano class
NVIDIA Jetson AGX Orin 64 GB
NVIDIA Jetson AGX Thor 128 GB
AI performance
67 TOPS (INT8, sparse)
275 TOPS (INT8, sparse)
Up to 2,070 TFLOPS (FP4, sparse)
GPU
Ampere, 1,024 CUDA cores, 32 Tensor cores
Ampere, 2,048 CUDA cores, 64 Tensor cores
Blackwell-class, 2,560 CUDA cores, 96 Tensor cores
CPU
6-core Arm Cortex-A78AE
12-core Arm Cortex-A78AE
14-core Arm Neoverse-V3AE
Memory
8 GB LPDDR5 · 102 GB/s
64 GB LPDDR5 · 204.8 GB/s
128 GB LPDDR5X · 273 GB/s
Storage(NGARi+ config)
512 GB NVMe SSD
1 TB NVMe SSD
2 TB NVMe SSD
Model range
7B–14B quantized
Up to 32B quantized (incl. qwen3.8)
70B–100B+ quantized, multimodal
Agents
6 included · 1–2 concurrent
6 included · all concurrent, plus custom
6 included · unlimited concurrent
Typical power
~25 W
15–60 W
40–130 W
Networking
GbE · optional Wi-Fi/BT module
Dual GbE · optional 10 GbE
Dual 10 GbE · high-speed fabric options
Form factor
Palm-sized, desk
Desk, small team
Desk or shelf, robotics/lab
Enclosure
NGARi-designed enclosure
NVIDIA AGX Orin developer-kit enclosure
NVIDIA AGX Thor enclosure
Operating range
0–45 °C ambient · fan-cooled · designed for continuous operation
Accelerator, TOPS, GPU, CPU, memory and power figures are the published capabilities of the corresponding NVIDIA Jetson modules that NGARi+ is built on. Storage and the pre-installed sovereign stack are NGARi+ configuration, as are the agent limits. Enclosures are not: NGARi+ Nano ships in a NGARi-designed enclosure, while NGARi+ Orin and NGARi+ Thor ship in NVIDIA’s own developer-kit enclosures.
What ships on it
Installed and ready on first boot
NS-BOS — the Sovereign Business Operating System
Open kernel, Apache 2.0 — inspect what runs on your machine
Six executive agents with email-first control
Whisper speech-to-text and Piper text-to-speech, on device
Hash-chained audit log, RBAC and compliance reporting
Mesh networking between your NGARi devices
Model manager: swap Qwen, Llama, Mistral, Gemma, Phi
In the box
One NGARi+ unit, integrated, flashed with the sovereign stack and tested before dispatch
Power supply matched to your region's plug type
Quick-start card (hostname, admin account, first model)
Recovery image on the internal NVMe — no USB stick required
Warranty and RMA card
No subscription is required for the device to be useful. Support plans and training are optional add-ons.
Why Jetson
We chose NVIDIA Jetson because it is the only edge platform that gives a small appliance data-centre class AI and a long, inspectable lifecycle. Arm64 Linux, unified memory, CUDA and TensorRT, and a module roadmap that keeps getting faster without changing the software contract.
Pictured: the NVIDIA Jetson AGX Orin Developer Kit — the reference hardware for the
module inside NGARi+ Orin. NGARi+ Orin ships in this enclosure, pre-installed and verified with the sovereign stack. NGARi+ Nano is the exception: it is the only model in the line that ships in a NGARi-designed enclosure.
Photo: Auledas, Wikimedia Commons, CC BY 4.0.
NGARi+ Nano and NGARi+ Thor are shown as illustrations — Nano pending its own production photography, Thor because no licensed photograph of NVIDIA’s AGX Thor enclosure is available.
Unified memory
The GPU and CPU share one memory pool, so a 27B model loads without shuttling weights across a bus — and there is no separate VRAM ceiling to hit.
Real toolchain
CUDA, TensorRT and the Jetson software stack are production-grade on aarch64. That is why our fine-tuning and distillation pipeline runs on the same silicon we sell.
Long lifecycle
Jetson modules have multi-year supply and software support windows. Buy once, and keep it useful — which is the whole point of ownership.
NGARi is an NVIDIA Inception member. NVIDIA and Jetson are trademarks of NVIDIA Corporation. NGARi+ is an independent product built on NVIDIA Jetson modules and is not endorsed or sponsored by NVIDIA.
The developer kit photograph is used under CC BY 4.0 with attribution, and depicts NVIDIA reference hardware rather than the NGARi+ product. Full source and licence record: assets-src/jetson/CREDITS.md.
Buy it, or get trained on it first
Hardware is only half of confidence. The other half is knowing what to do with it on day one. You have two honest paths.
Path one
Buy NGARi+ direct
You know what you want to run. The box arrives flashed, you set an admin account, pick a model and start. Best for teams that already have an AI plan.
Path two · recommended if this is your first sovereign deployment
Join AI-Corps, then own it
AI-Corps is our sovereign venture and workforce program. You get the same class of hardware pre-flashed, plus the curriculum, the clinics, and a credential that is anchored to the machine that earned it.
Studio Edition $1,999 · Orin Nano class (67 TOPS), 512 GB
Enterprise Edition $5,499 · AGX Orin (275 TOPS), 1 TB
Sovereign Frontier $8,999 · AGX Thor, 128 GB
Customer-discovery curriculum and weekly clinics
CSAO / CSSA credentials verified against your device fingerprint
Sovereign Hardware Credits earn toward up to 50% of a node
If you are deploying sovereign AI inside a team for the first time, AI-Corps is usually the better purchase: the failure mode of ownership is not the hardware, it is not knowing which workflow to move onto it first. If you already know, buy direct and keep the margin.
Buying, shipping and legal
Payment and shipping
Card payment through Stripe; USD pricing, taxes shown at checkout
Ships in production batches; your estimated window is shown at checkout
No. NGARi ONE is the palm-sized sovereign handheld. NGARi+ is the desk and team line built on NVIDIA Jetson modules — it runs bigger models, hosts all six agents at once, and is designed to sit in an office, lab or vehicle rather than a pocket.
What happens to my data?
It stays on the device. Nothing is transmitted for inference, telemetry is off by default, and the sovereignty meter can show outbound bytes from the network interface as proof. You can run the whole stack with the network cable unplugged.
Do I have to pay a subscription after I buy it?
No. The device is complete without one. Subscriptions exist for hosted agents, managed support and training, and for the API — none of them are required to use your hardware.
Can I put my own models on it?
Yes. The model manager supports open weights — Qwen, Llama, Mistral, Gemma, Phi and others — and you can import your own fine-tunes. The open kernel is Apache 2.0.
Which model does NGARi actually run?
The hosted preview and API currently serve ngari-ft-distilled-v5 — NGARi's own 1.5B model (Apache 2.0, a fine-tune of Qwen2.5-1.5B) — on our edge hardware. The larger 27B-class qwen3.8 is what NGARi+ Orin and Thor run locally, with no network in the loop.
Can I train on it?
Yes — Orin and Thor run fine-tuning and distillation locally, which is how our own distilled models were produced. Nano is intended for inference and small adapters.
Is there an enterprise or volume option?
Yes. Institutional licences cover on-prem clusters, white-label platform and curricula, and a dedicated team. Email [email protected] or start with Corps.
What if I am not sure which machine to buy?
Pick by model size. 7B–14B and one or two workflows: Nano. A 27B–32B model and the full C-suite: Orin — that is the machine we run in production ourselves. Training, vision or robotics: Thor. If you want help deciding, join an AI-Corps clinic first.
Own your silicon. Own your intelligence.
Every question you ask a rented model is a payment and a disclosure. NGARi+ makes it neither.
Installment plans are part of the offer on all three NGARi+ appliances, and on every Corps Edition tier. Each appliance can be reserved over 2 or 4 monthly payments. A plan changes when you pay, never how much: the payments add up to the list price exactly, with no interest and no fee. Your node is flashed, configured and shipped once the plan is complete — or immediately if you pay in full.
Every plan above is live: the buttons on each appliance and the amounts in this table check out at exactly the figures shown — you are never charged an amount you did not agree to. Prices are USD; each plan's payments sum to the one-time price.
