We take cryptocurrency — so the coins you hold can buy real hardware.Pay in crypto, spend it on real hardware. Free insured shipping worldwide over $399. Plain, unbranded boxes, sent from Germany.Free insured shipping over $399. Your rate is locked for 30 minutes once checkout opens.Rate locked 30 minutes. Every item sealed, serial-checked and covered by a 24-month warranty.Sealed, 24-month warranty.

Saved items Sign in

GIGABYTE

GIGABYTE 25FC9-RTX001-P2R ai accelerator card 96 GB GDDR7 24064 CUDA

SKU CH-BHGD-8EWRE MPN 25FC9-RTX001-P2R

AI accelerator with 96 GB GDDR7 ECC memory and 24064 CUDA cores for large-model training and rendering

  • InterfacePCI Express 5.0 x16
  • Chipset ManufacturerNVIDIA
  • GPURTX PRO 6000 Blackwell Workstation Edition
  • CUDA Cores24,064
  • Memory Size96GB
  • Memory TypeGDDR7 with ECC
  • 96 GB GDDR7 memory with ECC keeps massive models resident
  • 24,064 CUDA cores accelerate parallel compute for AI and rendering
  • PCI Express 5.0 x16 interface delivers high-throughput data transfer
  • Four DisplayPort 2.1 outputs drive multiple high-resolution displays
  • 600 W maximum power draw matches workstation cooling capacity

Professional AI Workstation GPU

The GIGABYTE 25FC9-RTX001-P2R is a professional AI accelerator card built on the NVIDIA Blackwell architecture. It delivers 24,064 CUDA cores and 96 GB of GDDR7 memory with ECC for data integrity. The card connects through a PCI Express 5.0 x16 interface and draws up to 600 W of power.

Suited for Large-Model Training

Researchers and engineers training large language models or running complex simulations will benefit from the 96 GB frame buffer and fifth-generation Tensor cores with FP4 support. Creative professionals driving four DisplayPort 2.1 monitors at high resolution also fit this profile. Buyers who need more than 96 GB of VRAM or who lack a 600 W power budget should consider other options.

96 GB GDDR7 Frame Buffer with ECC

The 96 GB capacity comfortably holds large model weights, high-resolution textures and extensive datasets in a single GPU. ECC protection guards against silent data corruption during long compute runs. Workloads exceeding 96 GB will require multi-GPU configurations or CPU offload, which introduce latency and complexity.

Highlights

  • 96 GB GDDR7 memory with ECC keeps massive models resident
  • 24,064 CUDA cores accelerate parallel compute for AI and rendering
  • PCI Express 5.0 x16 interface delivers high-throughput data transfer
  • Four DisplayPort 2.1 outputs drive multiple high-resolution displays
  • 600 W maximum power draw matches workstation cooling capacity

Specifications

BrandPNY
ModelRTX PRO 6000 Blackwell Workstation Edition
Part NumberVCNRTXPRO6000B-PB
InterfacePCI Express 5.0 x16
Chipset ManufacturerNVIDIA
GPURTX PRO 6000 Blackwell Workstation Edition
CUDA Cores24,064
Memory Size96GB
Memory TypeGDDR7 with ECC
DisplayPort4 x Display Port 2.1
Shipping weight2.29 kg
Package size381 × 216 × 76 mm

Questions about this item

What power supply capacity is needed for the 600 W max power draw?

A power supply rated above 600 W with a 16-pin connector is required to deliver the 600 W maximum power consumption.

Will this PCI Express 5.0 x16 card run in a PCI Express 4.0 motherboard slot?

Yes, the card is backward compatible and will operate at PCI Express 4.0 x16 speeds in a 4.0 slot.

How can I confirm the 24064 CUDA cores are recognised after installation?

Open NVIDIA Control Panel or run nvidia-smi; both will list the GPU with 24064 CUDA cores and 96 GB GDDR7 memory.

New to this? Buying server hardware with crypto — what to check, what it costs to pay, and what is never asked for.

Also in this aisle

People compared these

Same shelf, same checkout — eight coins and a 30-minute rate lock.