lycompute.Get early access
INDEPENDENT COMPUTE. AMBITIOUS IDEAS.

Your next idea.
More compute.

Private inference. Fine-tuning.
On GPUs reserved for you.

Run and adapt open models on dedicated hardware, instead of sending your prompts and data to a shared model API.

Enquire about early accessPrelaunch · Built for AI developers & teams
YOUR MODELS. YOUR DATA. YOUR GPU.PRIVATE AI COMPUTE
DEDICATED GPU COMPUTE

Your own models.
On your own terms.

Inference and fine-tuning on hardware
reserved for you, not a shared API.

Illustration of a GPU accelerator chip with memory stacks and glowing circuit traces
Built for private AIFIRST MACHINE: NVIDIA DGX SPARK
For teams who want their own models, without buying hardware.See what you can run
01 — WHAT YOU CAN RUN

Keep it private.
Make it yours.

Keep sensitive prompts and datasets off third-party model APIs.
Serve open models privately.
Adapt them to your domain.

PRIVATE INFERENCE / FINE-TUNING
01

Private inference

Serve open-weight LLMs behind your own endpoint. Your prompts and outputs stay on a machine dedicated to you, not a shared model API.

INFERENCEPRIVACY
02

Fine-tuning

Adapt open models to your domain with your own datasets, from LoRA and QLoRA to full fine-tunes where memory allows.

FINE-TUNINGLORA
03

Evaluate and prototype

Benchmark models, test retrieval pipelines and agents, and validate a workload before scaling it up.

EVALUATIONAGENTS
02 — THE HARDWARE

Starting with DGX Spark.

Our first machine, with more GPUs to follow.
We match the hardware to your workload.

128GB

Unified system memory

CPU and GPU share one coherent memory pool, giving large models more room to work.

1PFLOP*

AI compute performance

NVIDIA GB10 Grace Blackwell brings a new generation of AI compute to your experiments.

200B*

Parameter model support

Explore inference with large models on a single system, depending on model and precision.

*Up to 1 PFLOP at FP4 with sparsity. Model capacity depends on quantization and workload; these are hardware specifications, not hosted performance guarantees. NVIDIA specifications

03 — GET IN EARLY

Your workload.
Let’s make room.

We’re preparing the first Lycompute rentals, starting with NVIDIA DGX Spark. Tell us what you want to run, inference or fine-tuning, and when you need it. We’ll discuss fit, pricing, and availability before you commit.

FROM €129 / WEEK · 1-WEEK MINIMUMEarly access from €99/week. No payment required to enquire.

Opens an email draft for you to review and send.

Prefer email? contact@lycompute.com
A FEW THINGS TO KNOW

Before you build.

Can I rent a machine today?

Yes. Rentals are booked by the week, with a one-week minimum. The machine is yours alone for the whole booking, and storage is wiped before the next customer. Our booking calendar opens soon; until then, send an enquiry with your dates and we’ll reserve them with you.

What will a rental cost?

€129 per week, or €429 per 4-week block. Early access customers get their first bookings at €99 per week. Need a longer or custom arrangement? Tell us about your workload and we’ll work it out with you.

Where does my data go?

Your workload runs on a machine dedicated to you, rather than a shared model API. Tell us about your data requirements in your enquiry and we’ll walk you through access, storage, and isolation before you commit.

Which GPUs are available?

We’re starting with NVIDIA DGX Spark and plan to add other GPUs over time. Tell us what your workload needs so we can match the right hardware.

Is DGX Spark the same as renting an H100?

No. DGX Spark uses the NVIDIA GB10 Grace Blackwell Superchip with 128 GB of unified system memory. It is designed for AI development, prototyping, and inference. Its memory, bandwidth, and performance characteristics differ from datacenter GPUs.

Will my software run on DGX Spark?

DGX Spark runs an Arm-based CPU and NVIDIA’s AI software stack. Your containers and dependencies need compatible Arm64 builds and GPU support. Include your framework and model in your enquiry so we can discuss compatibility.

Is Lycompute affiliated with NVIDIA?

Lycompute is an independent service. NVIDIA, DGX Spark, and related marks belong to NVIDIA Corporation. No partnership or endorsement is implied.