Home/Used Equipment/Data Center GPUs

Used Data Center GPUs

Buy used data center GPUs, source repair spares or sell surplus. Provide itemized usage, configuration, repair and test information for individual items or bulk lists.

Product category illustration; verify the model, interfaces, configuration and used condition against actual product documentation.
Compute & Servers · Used Equipment

Data Center GPUs

Data-center GPUs

Source data center GPUs for AI training, inference, simulation and parallel computing, with the configuration matched to workload, accelerator memory and server platform.

Applications
Large-model training and inference, scientific computing, graphics and video processing, and cluster expansion.
Supply Scope
PCIe GPU cards · GPU modules supplied with a compatible server · Single- and multi-GPU configurations
Information for an Inquiry
Complete model or configuration, quantity, equipment location or destination, and required dates. Quote, condition, accessories and warranty are confirmed separately.
Used equipment checks

Confirm configuration and condition separately

Review the checks for this category. Provide available tests, test conditions and outstanding uncertainties separately.

Common Types & Supporting Components

  • PCIe GPU cards
  • GPU modules supplied with a compatible server
  • Single- and multi-GPU configurations
  • Compatible air- or liquid-cooling options
Typical Applications

Large-model training and inference, scientific computing, graphics and video processing, and cluster expansion.

Key Specifications

Workload
Model size, training or inference, concurrency and software framework
Accelerator Memory
Capacity, memory type and multi-GPU configuration
Platform
Card form factor, PCIe generation, dimensions and server support list
Power Supply
Power consumption, connectors and system redundancy headroom
Cooling
Active or passive cooling, airflow path or cold-plate requirements
Delivery Scope
Cards, adapters, cables, licenses and system validation scope

Four Priority Checks

  1. 01
    Provide the application, operating age and repair or replacement history
  2. 02
    Check accelerator memory, stress-test results and recorded errors, with test environment and date
  3. 03
    Inspect heatsinks, power connectors, board deformation and known damage
  4. 04
    Distinguish standalone cards from modules; check original system restrictions, accessories and after-sales scope

Actual Product Documentation & Delivery Terms

Itemize quantity, equipment location, actual photos, usage, repairs, known defects and available tests by model, serial number or asset tag. Identify untested or unverifiable information and provide test date, environment, method and results together.

Confirm quotation, packaging, freight, acceptance, warranty, returns and applicable cross-border terms for the actual goods. Label used, unused stock, refurbished, repair-required and scrap items separately. For equipment with storage media, confirm prior-data handling and removal of management accounts.

Equipment InquirySubmit a Project

Product category illustration

Product category illustration

Category illustration only. Refer to the specific product documentation for the actual model, configuration, condition and appearance.

Privacy Notice