Name: Lucebox Zero 495
Brand: Lucebox
Availability: PreOrder

Question 1

What is Lucebox?

Accepted Answer

A plug-and-play workstation for local AI inference. It runs headless on Ubuntu Server: set it up from your laptop or phone, manage it from the browser, and point your tools at it over the network. It arrives with our open source inference engine, tuned models, custom kernels, and speculative decoding ready to use through a single CLI. What a local inference PC is: /local-inference-pc

Question 2

What hardware is inside?

Accepted Answer

An AMD Ryzen AI MAX+ PRO 495 with 128GB or 192GB of LPDDR5X-8533 unified memory, an AMD Radeon AI PRO R9700 with 32GB of GDDR6, a 2TB or 4TB NVMe 1.4 SSD, and a 1000W 80+ Platinum SFX power supply. The extruded aluminium chassis, anodized black, has a volume of 11.97 litres.

Question 3

What does it cost?

Accepted Answer

The Lucebox Zero 495 starts at $5,999 USD per machine for the Developer tier (individuals), with 128GB of memory and 2TB of storage, and at $7,999 USD for the Business tier (teams), which includes one year of Lucebox Engine Pro. 192GB of memory adds $2,000, 4TB of storage adds $250, and the cluster kit is $799 per machine. That is the launch price for the first 200 units, $1,000 off the $6,999 list price. Import duties and worldwide shipping are included, and so are taxes outside the United States. In the US, no sales tax is added at checkout on shop.lucebox.com. Nothing is due on delivery.

Question 4

When does it ship?

Accepted Answer

Deliveries of the first Lucebox Zero 495 batch are expected in January 2027. The shop emails your receipt right away and we email tracking the day your machine leaves.

Question 5

How do I pay?

Accepted Answer

On shop.lucebox.com, by card or with Shop Pay. The shop collects the payment and your shipping address, then emails the receipt and order number and confirms what happens next. The price includes import duties and shipping, and taxes outside the United States. In the US, no sales tax is added at checkout. Nothing is due on delivery.

Question 6

Can I order multiple units?

Accepted Answer

Yes. You can take up to 5 machines in one checkout. For more than 5, book a call and we prepare a single quote and invoice for the team. Book a Lucebox call: https://cal.com/apuppo/lucebox

Question 7

What is the cluster kit?

Accepted Answer

A Mellanox ConnectX-5 CX556M networking card with two 100 GbE ports, installed and configured in your Lucebox before shipping, plus the cable. It is sold per machine, $799 each, and you can add it to a single Lucebox. To cluster two Luceboxes, add the kit to both, connect the cable and they work together with nothing to install. One kit also links a Lucebox to another machine with a 100 GbE port.

Question 8

What is Lucebox Engine Pro?

Accepted Answer

The service tier around the open source engine: white-glove install, direct chat support with our engineers, priority delivery, custom model tuning, implementation help, and security hardening. It costs $199 per month per machine; one year is included with the Business tier and it can be added to any Lucebox.

Question 9

Is the software open source?

Accepted Answer

Yes. Our inference work is public at github.com/Luce-Org/lucebox, with 55+ contributors and 650+ pull requests. It includes hand-tuned kernels, DFlash speculative decoding, PFlash prefill, and hybrid-model optimizations.

Question 10

What models can I run?

Accepted Answer

Far more than fits in 32GB of VRAM: the engine runs one model across the R9700 and up to 192GB of unified memory, so the 284B DeepSeek V4 Flash fits. The engine ships tuned for Qwen3.8-27B and DeepSeek V4 Flash, and also runs Laguna XS 2.1, Gemma 4 and Ling 3.0 Flash with its drafters. You can bring your own GGUF; the CLI loads it. See the models: /engine#models

Question 11

Can I run other inference engines?

Accepted Answer

Yes. Lucebox runs Ubuntu Server with AMD ROCm and gives you full root access, so you can install other open source inference engines as on any Linux machine. The Lucebox engine is the one that comes installed and tuned for this hardware.

Question 12

Can I use it with Claude Code, Cursor, and OpenCode?

Accepted Answer

Yes. Lucebox exposes OpenAI-compatible and Anthropic-compatible endpoints. Point a supported client or agent harness to the Lucebox base URL and keep using its normal workflow.

Question 13

What about Ollama and LM Studio?

Accepted Answer

Lucebox does not require either one. It exposes an OpenAI-compatible endpoint, so tools that accept a custom base URL can connect directly while Ollama and LM Studio remain available for any separate workflows you already use.

Question 14

Does it need internet?

Accepted Answer

No. Lucebox runs fully offline once your model is loaded. Internet is only needed for updates and the optional cloud fallback.

Question 15

Can I use it away from home?

Accepted Answer

Yes. During setup you sign in to Tailscale from a link and approve Lucebox, or add it later from Manage. With Tailscale on your laptop or phone, signed in to the same account, you reach Manage and the private API over an encrypted tunnel from any network, at home, in the office or on the road, without opening a router port or exposing anything to the public internet. Point Claude Code, Codex, OpenCode or any compatible client at the tailnet address and keep working. Skip it at setup and everything still works on your home network.

Question 16

How loud is it?

Accepted Answer

Quiet at idle; the Radeon AI PRO R9700 cooling becomes audible during sustained inference. Most people keep it where fan noise does not matter and reach it over the network, so it never has to sit on your desk. The chassis directs hot air out the back.

Question 17

What's the power draw?

Accepted Answer

Around 500 watts under full inference load, with up to 300 W for the Radeon AI PRO R9700 and the remaining system power allocated to the Ryzen platform and components. Idle consumption is approximately 40 W. Plug it into any standard wall outlet.

Question 18

What's the warranty?

Accepted Answer

1 year on the full machine, parts and labor. We replace or repair any unit that fails under normal use.

Question 19

Can I SSH in?

Accepted Answer

Yes. Full root access. It is your machine. Open the shell, install whatever you want, run whatever you want.

Question 20

What about cancellations, returns and refunds?

Accepted Answer

You can cancel for a full refund at any point before your machine ships: email support@lucebox.com with your order number. After delivery you can return it within 14 days of delivery, complete and undamaged, with return shipping on you. Outside the EU and the UK a 25% restocking fee is deducted from the refund; buyers in the EU and the UK pay no restocking fee. A unit that arrives damaged, is dead on arrival, or develops a fault covered by the warranty is repaired or replaced at no cost.

Question 21

Do you ship internationally?

Accepted Answer

Yes. We ship worldwide from Italy, and shipping is included in the price. VAT, import duties, taxes and customs fees are included too: we pay them, so there is nothing to pay on delivery. In the United States, no sales tax is added at checkout. If a carrier ever asks you for a duty or tax payment, write to support@lucebox.com before paying. The shop collects your shipping address at checkout.

Question 22

Can I run multiple models at once?

Accepted Answer

Yes. Up to 192 GB of unified memory plus 32 GB of VRAM lets you keep a hot model resident in VRAM while a second sits in unified memory ready to swap in. The CLI handles loading and routing per request.

Question 23

Can several people use it at the same time?

Accepted Answer

Yes. Lucebox serves concurrent requests from several users, or from one user running several agents. Partial tensor parallelism and attention paging keep throughput up as users join. Memory is the first limit: if everyone runs 256K to 1M contexts it gets tight, and we work out a setup for that case with you.

Question 24

How does speed hold up with several users?

Accepted Answer

At 4 to 8 concurrent users, expect each user's generation speed to drop by 10 to 20% at most. If one user gets 100 tok/s on a model, four users each get about 80 to 90 tok/s, roughly 360 tok/s combined. We publish multi-client benchmarks on the blog as they become available.

Question 25

How does it compare with the DGX Spark for several users?

Accepted Answer

On paper the DGX Spark has more TFLOPs. Lucebox's custom speculative decoding models and server-side tensor parallelism put it ahead in delivered speed, for one user and for several. The engine page collects the published comparisons.

Your Inference Workstation.

Private, always on, ready out of the box.

Your data stays private

Built for coding agents

Always on, no meter

Optimized for speed from the startOptimized for speed

Two processors, one engine, built for speed.

Only a heterogeneous setup gives you big models and speed.

Over 2× the reported DGX Spark decode speed, at the same price.

Qwen3.8-27B

DeepSeek V4 Flash

Easy setup. Use it in the apps on your laptop.

Open the setup page

Pair and connect

Continue in Manage

Connect your apps

Monitor your Lucebox

Order your Lucebox Zero 495.

Developer

Configure yours

Proudly open source, and built in public.

We share what we learn.

Running DeepSeek V4.1 Flash on the Lucebox memory hierarchy: up to 3x faster with the R9700

Vision LLM inference: Lucebox has 3.2x the throughput of NVIDIA DGX Spark

Inference-aware cooling: 29% less fan speed on the AMD R9700, same temperatures

3.63× the DGX Spark on DeepSeek V4 Flash

KVFlash: 256K context with 72 MiB of KV

DeepSeek V4 Flash on the Ryzen AI MAX+ 395

Frequently Asked Questions

Own your intelligence.