GPU rental · dedicated hardware

Dedicated NVIDIA DGX Spark — €495/month

Your own 128 GB GB10 Grace-Blackwell machine in Stockholm, Sweden — a named, single-tenant physical system on monthly rental from hardware AxForge owns and operates. Your model, your traffic, our machine.

eu-se-1 · Stockholm, Sweden Single-tenant · dedicated €495 / month excl. VAT
Rent DGX Spark View benchmarks Talk to an engineer Launch pricing. Request a machine — an engineer confirms availability and provisioning with you. Cancel before renewal.

Specifications

What you rent

SystemNVIDIA DGX Spark — dedicated, single-tenant
SuperchipNVIDIA GB10 Grace-Blackwell — see the GB10 page
Memory128 GB unified, shared CPU/GPU
CPU architectureARM64
TenancyDedicated — a named physical machine assigned to you, not shared capacity
Rental termMonthly — cancel before the next renewal
Pricing€495 / month (launch pricing, excl. VAT)
Regioneu-se-1 · Stockholm, Sweden

Performance

What this machine does, by workload

Example workloadModelCommunity benchmarks*
Fast agents / reasoning (MoE)Qwen3.6 35B-A3B · NVFP4 + MTPup to 86.3 t/s
Coding (MoE)Qwen3-Coder 30B-A3B~42–61 t/s
Dense reasoningQwen3.8 27B · NVFP4 + MTP25.1 t/s
Smaller dense LLMQwen3 8B · Q4~42 t/s
Large MoEDeepSeek V4 Flash · 180B, 13B active~23 t/s

*Community results (SparkBench PBM @ 4k, llama.cpp) — labelled, not ours; they vary by runtime, quantization, context length and serving configuration. Full tables, sources and the MoE-vs-dense story on the GB10 page. The same hardware also serves image generation and editing — see the model catalogue.

Fit

What a DGX Spark is for

Use caseWhy it fits
Dedicated inference, ~7B–35B models128 GB unified memory holds model weights and KV cache in one pool — the measured numbers above are exactly this workload.
Private inferenceA single-tenant machine in an EU region. Your model, your traffic, our hardware — prompts never persisted.
Dev / staging nodesA named machine you keep for the month — a stable target for integration, load testing and pre-production serving.
Model evaluationRun bake-offs on the exact hardware class you would serve from, with results that transfer.
AI agentsHost agent runtimes next to their model — long-running processes with no per-token surprise from a third party.
Fine-tuning experimentsThe unified memory pool fits adapters and smaller fine-tunes that would need careful sharding elsewhere.
Self-managed serving & containersBring your own serving stack — vLLM, llama.cpp, custom containers — and run it your way on your machine.

Searching for DGX Spark cloud or DGX Spark hosting? Same machine: you rent a named physical system, we host and operate it, you reach it over the network.

ARM64

It's an ARM64 machine — here's what that means

The GB10 platform is ARM64, not x86. Most modern AI frameworks and container images ship ARM64 builds — our own production serving stack runs on it. x86-only binaries need ARM64 builds or rebuilds. Not sure about your stack? An engineer can review it with you before you commit.

How it works

From request to running workload

1Create an account — or talk to an engineer first if you want the stack reviewed.
2Request a DGX Spark from the console's GPU area.
3An engineer confirms availability and provisions your machine — provisioning is engineer-led, not automated.
4Connect and deploy your models, containers and tools over remote access.
5Keep it monthly at €495/month — cancel before the next renewal.

Data & privacy

Your model, your traffic, our hardware

Prompts never persisted. Requests to your dedicated DGX Spark are processed in memory in Sweden — not written to disk, not logged, not retained, never used to train anything. We keep only request metadata (token counts, timestamps, status) for billing and operations. Full policy at axforge.ai/privacy.

FAQ

DGX Spark rental — common questions

Can I rent a DGX Spark today?

Yes — machines are rented monthly from Sweden (eu-se-1), subject to current capacity. Talk to an engineer to claim one; they confirm availability with you.

How does provisioning work?

Provisioning is engineer-led: you request a machine (or talk to us first), an engineer confirms availability and compatibility, then sets up your dedicated DGX Spark and hands you remote access. From there you deploy your own models, containers and tools.

What workloads can I run?

Anything that fits a 128 GB ARM64 machine you fully control: dedicated inference of ~7B–35B models, agents, fine-tuning experiments, evaluation, dev/staging, and your own serving stack in containers. If you only need per-token inference, the serverless Qwen API may be enough — no machine required.

What does DGX Spark rental cost?

€495 per month for a dedicated machine (launch pricing). We watch the market and price under it: that is 90% of the lowest listed dedicated DGX Spark rental we found on 2026-08-26. An engineer scopes the configuration with you.

What models run well on a DGX Spark?

Dense models of roughly 7B–35B — and MoE models far larger: community benchmarks run 80B–180B MoE at usable speeds, because only the active experts are read per token. Full tables and sources on the GB10 page.

Is DGX Spark hosting the same as DGX Spark cloud?

On AxForge you rent a named physical machine, hosted and operated by us in an EU region, reachable over the network like any cloud endpoint — but it is your dedicated system, not a shared cloud instance.

DGX Spark is ARM64 — will my stack run on it?

The GB10 platform is ARM64. Our own serving stack runs on it in production — the published numbers were measured there. x86-only binaries need ARM64 builds; an engineer can review your stack before you commit.

Are my prompts stored on a rented DGX Spark?

No. Your model, your traffic, our hardware — prompts never persisted. Only request metadata (token counts, timestamps, status) is kept for billing and operations — see the privacy policy.

Need a machine scoped to your workload?

Rent DGX Spark Talk to an engineer

Explore

All GPUs

© 2026 AxForge · EU-hosted AI infrastructure Pricing Docs Trust Privacy Terms