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

  • Graphics processorRTX PRO 6000 Blackwell Workstation Edition
  • Memory capacity96 GB
  • Interface typePCI Express 5.0 x16
  • CUDA core count24,064
  • Type of memoryGDDR7 with ECC
  • Chipset makerNVIDIA
  • 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.

How it compares

Measured against everything we stock in GPUs for AI & Data Centers, at today’s prices. Recalculated every night.

Price $12,387.99
Pricier than about 80% of the 36 comparable items (median $5,369.99).
Memory capacity 96 GB
Higher than about 80% of the 12 comparable items (median 79 GB).

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

Specifications

Product
Brand namePNY
Model nameRTX PRO 6000 Blackwell Workstation Edition
Part numberVCNRTXPRO6000B-PB
Memory
Type of memoryGDDR7 with ECC
Graphics
Graphics processorRTX PRO 6000 Blackwell Workstation Edition
Memory capacity96 GB
CUDA core count24,064
Chipset makerNVIDIA
Ports & slots
Interface typePCI Express 5.0 x16
DisplayPort connectors4 x Display Port 2.1
Size & build
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.

More in GPUs for AI & Data Centers

Similar items