+49 6430 9227117
NVIDIA DGX LEGACY · TPM FOR DGX-1 / DGX-2

NVIDIA DGX-1 / DGX-2 Maintenance — bridge service for older DGX generations

We service older NVIDIA DGX platforms (DGX-1 with Pascal P100 or Volta V100, DGX-2 with 16x V100 and NVSwitch) as bridge service until refresh strategy. With refurbishing pools for main components (V100 GPU boards, power supplies, NVSwitch modules) and SLA up to 24×7×4. Important honesty: DGX hardware is proprietary, component availability for DGX-1/-2 is structurally weak today. For very old fleets, refresh to DGX A100/H100 is often more economical than TPM bridge — we make this transparent in risk assessment before contract conclusion.

Which DGX Legacy models we service

DGX-1 was NVIDIA's first generation of complete AI training servers (released April 2016 with Pascal P100, refresh 2017-2019 with Volta V100). DGX-2 extended the concept (released 2018) with 16 V100 GPUs and the first generation NVSwitch interconnect. Both lines are technically still usable for AI inference and smaller training workloads, but no longer powerful enough for modern LLM training or MoE models.

DGX-1 · Pascal generation (older)
DGX-1 with 8x Tesla P100 (2016-2017)
DGX-1 · Volta generation
DGX-1 with 8x Tesla V100 16GB / V100 32GB (2017-2019)
DGX-2 · 16x V100 with NVSwitch
DGX-2 (16x V100 32GB, 2 PFLOPS, NVSwitch Gen 1)
Components (refurbishing pool)
P100/V100 GPU boards · NVSwitch Gen 1 · power supplies · mainboards

Why (or why not) TPM for DGX-1 / DGX-2

DGX-1/-2 maintenance is not trivial. Unlike standard server EOSL (Supermicro X9, F5 s-series, etc.), DGX hardware is proprietary — NVLink, NVSwitch, P100/V100 GPU boards with NVIDIA-specific firmware. Refurbishing pools for DGX-1/-2 are structurally thinner than for standard servers, and some critical components (NVSwitch Gen 1, early V100 boards) are scarcely available on the open market. NVIDIA offers standard support for DGX-1/-2 only limited or not at all — those who stay here often have no OEM service option. TPM is a bridge service solution with clear risk disclosures.

We recommend DGX-1/-2 TPM in two scenarios: (1) AI inference workloads that don't strictly need state-of-the-art hardware — DGX-1/-2 are technically still usable for many inference use cases, TPM extends productive lifespan economically. (2) Bridge service between DGX-1/-2 EOSL and a planned refresh phase to DGX H100/H200 or GB200 — TPM typically bridges 6-18 months until refresh hardware is available and installed. For very critical productive AI training workloads on DGX-1/-2 we recommend refresh instead of TPM bridge — modern DGX generations are 10-50x more powerful and energy efficient.

30–70 %
Savings vs. NVIDIA conditions (where available)
Bridge service
6-18 months until refresh to H100/H200/GB200
Honest disclosure
Refurbishing pool status per model before contract
Inference-suitable
DGX-1/-2 sufficient for many inference use cases

Generations timeline & TPM coverage

Per hardware generation: vendor phase (slate) and TechCare coverage window (teal) up to ~5 years post-OEM EOSL.

EOSL status of DGX Legacy generations

DGX-1 and DGX-2 are completely EOSL. NVIDIA factory warranty has expired for all configurations, standard support only limited available.

Model family Released OEM support ends TPM status
DGX-1 (Pascal, 8x P100) 2016 2022–2023 Recommended
DGX-1 (Volta, 8x V100 16GB) 2017 2023–2024 Recommended
DGX-1 (Volta, 8x V100 32GB) 2018 2024 Recommended
DGX-2 (16x V100, NVSwitch Gen 1) 2018 2024–2025 Recommended

As of 2026. EOSL data based on official vendor roadmaps and subject to change. Binding case-by-case information available on request.

What we deliver

OEM components

Our warehouse and certified refurbishing sources for DGX and Mellanox.

DGX specialist engineer

German-speaking technicians with NVLink/NVSwitch training, 4-hour response time guaranteed.

Flexible SLA per system

Parts Only, 5×9 NBD or 24×7×4 — freely combinable by location and criticality.

Multi-vendor contract

One contract for DGX, Mellanox and all other vendors. AI cluster stack consolidation.

Risk assessment

Component pool status per model before contract conclusion — honest disclosure.

CUDA & AI software stay

CUDA, AI Enterprise, Base Command Manager independent of hardware maintenance.

FAQ on DGX Legacy maintenance

Which DGX Legacy models do you service?
DGX-1 and DGX-2 in all configurations: DGX-1 with 8x Tesla P100 (Pascal, 2016-2017), DGX-1 with 8x Tesla V100 16GB or 32GB (Volta, 2017-2019), DGX-2 with 16x V100 32GB and first generation NVSwitch (2018-2020). Including refurbishing pool coverage for GPU boards (P100, V100 16/32GB), NVSwitch Gen 1, power supplies and mainboards. Pool depth varies per component — we make status transparent before contract conclusion.
What does TPM cost for DGX-1 / DGX-2?
30 to 70 percent savings (where NVIDIA conditions still available at all). A DGX-1 V100 32GB with 24×7×4 (if NVIDIA still offers premium support) typically 18,000-28,000 EUR/year, with TechCare 7,000-12,000 EUR. DGX-2 (16x V100) similarly higher absolute: 30,000-45,000 EUR NVIDIA, 12,000-18,000 EUR TechCare. For many DGX-1/-2 fleets NVIDIA no longer offers support — TPM is then the only service option.
How is component availability for DGX-1/-2 really?
We're honest: structurally weak but addressed with certified refurbishing sources. P100 GPU boards (DGX-1 Pascal) are rare on market today — we have pool coverage but for multi-board failures lead times are possible. V100 16GB/32GB boards (DGX-1 Volta, DGX-2) are still available in certified refurbishing sources. NVSwitch Gen 1 (only DGX-2) is the most critical component — on NVSwitch failure the DGX-2 can no longer operate in full topology, reduction to without-NVSwitch config is possible but performance loss significant. Power supplies and mainboards uncritically available. We create a risk assessment per DGX model and component before contract conclusion.
When should we refresh to modern DGX (H100/H200/GB200) instead of TPM?
Three clear refresh indicators: (1) Active AI training workloads (LLMs, computer vision, multi-modal) on DGX-1/-2 — modern DGX generations are 10-50x more powerful, ROI on refresh investment is typically under 12 months performance gain. (2) Energy efficiency: DGX-1/-2 have significantly higher power-per-performance than H100/H200 — with rising electricity prices refresh pays off faster. (3) AI software stack requirements: newer PyTorch/CUDA versions, newer Triton inference features, Transformer Engine only available on H100+. TPM is right choice for: inference workloads without state-of-the-art requirements, test/dev environments, bridge service until refresh hardware is available (often 6-18 months lead time for H100/H200/GB200).
Do CUDA and AI software continue to work on DGX-1/-2?
Yes, with restrictions. CUDA toolkit, GPU drivers for P100/V100 and standard AI frameworks (PyTorch, TensorFlow) continue license-free. CUDA versions are still supported by NVIDIA for older compute capability (P100=6.0, V100=7.0) for a while, but newest CUDA releases (12.x with Hopper optimizations) bring no advantage on P100/V100. Transformer Engine, FP8 operations and some newer Triton inference features are hardware-limited to H100+ — not available on DGX-1/-2. For standard AI inference and smaller training workloads, software stack coverage is sufficient.
Which SLA levels do you recommend for DGX Legacy?
Strongly depends on workload criticality: DGX-1/-2 in productive AI inference workloads (customer-facing pipelines): 24×7×4 with German-speaking onsite engineer is standard. For DGX-1/-2 as backup compute or in test/dev environments: 5×9 NBD typically sufficient. For DGX-1/-2 in refresh bridge phase (parallel to newly ordered H100/H200): Parts Only or 5×9 NBD sufficient — refresh hardware takes over productive load successively. For very old DGX-1 Pascal fleets running as pure lab servers: Parts Only with 14-day delivery time as most economical option.
Can we have DGX Legacy and current DGX in the same contract?
Yes. Multi-class NVIDIA contracts are exactly for these mixed fleets — DGX A100/H100/H200/GH200/GB200 (current generations) plus DGX-1/-2 (Legacy) plus Mellanox adapters and switching — all in one contract, one point of contact, one SLA report set. For DGX refresh projects this is ideal: TPM for legacy bridge phase plus TPM for new DGX hardware from warranty expiration, all consistently managed.
How fast do we get a risk assessment and quote?
Risk assessment within 5 business days after receipt of your inventory list with model, GPU configuration and serial number. Quote including component pool status per model. For critical workloads we offer on-site spare components as additional service option (negotiable in contract).
Service performance

Real actuals Q1 2026 — straight from our ITIL ticketing.

99,2 %
Tickets resolved within agreed response time
2,4 h
Avg. first response on 4h SLA tier
88 %
First-time fix on initial dispatch
97 %
Spare part on site within 4 h, DACH depots
More from NVIDIA

Other NVIDIA models and service