TCO research · as of November 2026 · all values net

Self-Hosted LLMs — buy or rent?

What does operating your own LLM infrastructure really cost — as a purchase (DGX Spark, DGX Station GB300, GB300 NVL72) or as bare-metal rental with full control during the rental period?

The key figures

All values EUR net (excl. VAT), calculation basis November 2026. Every figure comes from the generated calculation (calc/tco.md), every performance figure from public receipts (vLLM, SGLang, TensorFold) — nothing is estimated where a receipt exists.

20 tok/s/user
SLO for every task class (A1 RAG, A2 development, A3 IT automation)
€ 210,418
CAPEX of the GB300 pair (2× stations + 2× RTX 6000) — the team platform
~64 users
Break-even: from here, buying the GB300 pair beats Hetzner rental on cost per user
€ 3,599
Per month for the cheapest bare-metal node (Hetzner GEX430, 4× RTX PRO 6000, 384 GB) — one-time setup € 3,599

Method: receipts first

Three use-case profiles with shared requirements — the scenarios differ only in peak factor and model class.

A1 — Document research / RAG (NDA)

Peak factor 50%. Half the users run a concurrent research session at peak. Flash class (GLM-5.3-Flash, DeepSeek-V4.1-Flash).

A2 — Software & firmware development

Peak factor 80%. Agentic, long generations, large contexts — the cost driver. Frontier models (Kimi K3) only on GB300/NVL72 classes.

A3 — Internal IT automation

Peak factor 90%. Agents and workflows run continuously at high concurrency — flash class.

Mixed-load power model: Weff = idle + (load − idle) × duty cycle. Cooling +15%. Electricity is included in the rent for every rental option — no separate power line there.

Buying: the four candidates

Prices November 2026 (re-verified 2026-11-22; DGX Spark +9.6% since October, RTX 6000 −1.7%). Device classes come as pairs (N+1 inherent).

ConfigurationCAPEX netMonth idleMonth full load
DGX Spark GB10 2× cluster (256 GB)€ 9,575€ 301–316€ 332–373
DGX Spark GB10 4× cluster (512 GB)€ 19,150€ 602–632€ 665–745
2× DGX Station GB300 + 2× RTX 6000 (pair)€ 210,418€ 6,835–6,926€ 7,393–7,931
2× GB300 NVL72 (purchase, redundant)~€ 8.6M~€ 330,129–374,455

Which model runs where?

ClassLargest modelsDoes not run
Spark 2× (256 GB)GLM-5.3-Flash, Qwen3.8-Flash-Next, DS-V4.1-Flash only in low quants (fewer users)DS-V4.1-Flash Q3_K_M (347 GB) and everything above
Spark 4× (512 GB)+ DS-V4.1-Flash Q3_K_M/Q4_K_M, GLM-5.3 Int4-Int8MixDS-V4.1-Flash FP8 (510 GB), GLM-5.3 FP8 (756 GB), Kimi K3
GB300 pair (1,496 GB)All flash quants (FP8/NVFP4), GLM-5.3, DS-V4-Pro, Kimi K3 int3/1-bitGLM-5.3 BF16 (1,507 GB), Kimi K3 MXFP4 (1,561 GB)
2× NVL72 (~20 TB)Everything, incl. Kimi K3 MXFP4 and GLM-5.3 BF16—

Classification: DGX Spark is the entry tier (pilot, 16–64 users, flash workloads) with a planned exit at ~128 users. The team platform is the GB300 pair. Frontier-A2 scales only on 2× NVL72 from ~90 users.

Renting: bare metal with full control

Only dedicated bare-metal servers with full root access count — no hypervisors, no shared GPUs. 19 qualifying providers reviewed (full research).

Rental nodeVRAMMonth netOne-time setupLocation / provider
Hetzner GEX430 (4× RTX PRO 6000 Max-Q)384 GB€ 3,599€ 3,599Helsinki, Hetzner
8× RTX PRO 6000 Blackwell768 GB~€ 9,629n.v.Amsterdam, DataPacket
8× HGX B300 (Blackwell Ultra)2,304 GB~€ 35,040n.v.Gcore (no receipts — price reference)

Billing reality: Hetzner charges the one-time setup fee always — hourly billing included. Cancellation is to month end: a rental effectively runs 1–2 months minimum (setup + ~2 months ≈ € 10,797 for the GEX430). The hourly rate (€5.77/h) is almost theoretical for short projects.

NDA/IP data leaves the premises: Rental runs in the provider's data center (e.g. Helsinki). The same concern that excluded colocation applies here — rental is documented as a parallel scenario, not a replacement for the on-prem decision.

N+1 applies to rental too: every additional node is an additional rental contract (with its own setup fee). At small stages, redundancy roughly doubles the cost per user.

Buying versus renting: the break-even

Cost per user/month (mixed load, 36-month basis), A1 document research. The GB300 pair gets cheaper with occupancy; rental scales linearly.

A1 usersGB300 pair (buy)Hetzner GEX430 (rent)Spark 2× (buy)8× RTX PRO 6000 (rent)
16€ 454€ 462€ 41€ 1,204
64€ 114€ 116€ 41€ 301
128€ 57€ 116€ 41€ 150
256€ 28€ 116€ 41€ 150

At 64 A1 users, the purchased pair (€113.61) and the GEX430 rental (€115.59) are practically tied — the break-even. At 128 users the rental costs twice as much per user, at 256 four times. Note: the Spark cluster wins the per-user math at small stages but only carries flash classes and scales by device count — 128 A1 users need 32 GB10 devices.

€ 113.61 vs. € 115.59
Purchased pair versus GEX430 at 64 A1 users — the break-even point
2×
Rental cost advantage of buying at 128 users (€ 56.81 vs. € 115.59)

Run your own numbers

Pick a use-case profile and team size — the calculator shows required devices, total cost and cost per user for every purchase and rental option, straight from the generated calculation.

Open the TCO calculator

Sources

All monetary values EUR net (excl. VAT). Rental prices net as published by the providers; USD quotes converted at the ECB reference rate 0.90992 (2026-11-20). This page is a private, non-commercial presentation; no guarantee is given for completeness or currency.