Systems X86 Servers GPU Servers Storage Servers GPU Workstations Components Memory Modules SSD NAND Flash DRAM InfiniBand / Ethernet Open-Box New Used & Refurbished About Contact Promotion
Home / Promotions / NVIDIA Tesla P40
Tesla P40 GPU Accelerator

NVIDIA Tesla P40 24GB PCIe GPU Accelerator

Passive-cooled Pascal data-center GPU with 24 GB GDDR5 memory, PCIe 3.0 x16 host interface and 250 W board power for virtual workstation, rendering and inference workloads.

  • NVIDIA Pascal GPU with 3,840 CUDA cores.
  • 24 GB GDDR5 framebuffer with up to 347 GB/s memory bandwidth.
  • PCI Express 3.0 x16, dual-slot rack-server form factor.
  • 250 W total board power with passive cooling; system airflow is required.
  • NVIDIA product brief identifies INT8 support for deep-learning inference.
In stock 472 units available - New Manufacturer P/N 699-2G610-0200-100 Request a Quote

Product Overview

NVIDIA positions the Tesla P40 as a Pascal-generation GPU accelerator for virtualized visual computing, simulation, rendering and compute workloads. The official datasheet highlights support for Quadro vDWS software and CUDA/OpenCL workloads in virtualized environments.

The Tesla P40 product brief identifies the board as PG610 SKU 200 / NVPN 699-2G610-0200-100, with 24 GB GDDR5 memory, PCIe 3.0 x16 connectivity, passive thermal design and a 250 W maximum power limit.

For AI inference deployments, NVIDIA notes INT8 instruction support in the product brief, enabling high-throughput inference use cases when paired with a compatible system and software stack.

Key Highlights

Architecture
Pascal

One NVIDIA Pascal GPU according to the official Tesla P40 datasheet.

CUDA Cores
3,840

CUDA core count listed in NVIDIA's Tesla P40 product specifications.

Memory
24 GB GDDR5

Large framebuffer for graphics, visualization and compute workloads.

Board Power
250 W

Passive data-center card requiring host-system airflow.

Verified Capabilities

Compute and virtualization

  • vGPU profiles: Official datasheet lists 1 GB, 2 GB, 3 GB, 4 GB, 6 GB, 8 GB, 12 GB and 24 GB profiles.
  • NVENC density: NVIDIA lists support for 24 H.264 1080p30 streams.
  • Workload support: Datasheet references CUDA and OpenCL workloads with NVIDIA virtual GPU software.

Board integration

  • Host interface: PCI Express 3.0 x16 interface.
  • Thermal solution: Passive cooling; product brief states system airflow is required.
  • Auxiliary power: One CPU 8-pin auxiliary power connector listed in NVIDIA's product brief.

Technical Specifications

Product SKUPG610 SKU 200
NVIDIA NVPN699-2G610-0200-100
GPU architectureNVIDIA Pascal
CUDA cores3,840
Memory24 GB GDDR5
Memory interface384-bit
Memory bandwidthUp to 347 GB/s
Host interfacePCI Express 3.0 x16
Form factor4.376 in x 10.5 in, dual-slot
Total board power250 W
Thermal solutionPassive
Power connectorOne CPU 8-pin auxiliary power connector
Operating temperature0 C to 45 C
Storage temperature-40 C to 75 C
ConditionNew
Manufacturer P/N699-2G610-0200-100
Inventory listed date2026-04-29

Specifications are summarized from NVIDIA Tesla P40 GPU Accelerator Product Brief: https://images.nvidia.com/content/pdf/tesla/Tesla-P40-Product-Brief.pdf

Use Cases

Virtual Workstations

For environments using NVIDIA virtual GPU software to deliver remote visualization and design workloads.

Inference Servers

Pascal GPU with INT8 support can be used in compatible deep-learning inference deployments.

Rendering and Simulation

The official datasheet references simulation, HPC rendering, CUDA and OpenCL workloads.

Frequently Asked Questions

No. NVIDIA documents this board as passively cooled, so the server chassis must provide sufficient airflow.

The promotion SKU is tied to NVIDIA NVPN 699-2G610-0200-100, also identified in the product brief as PG610 SKU 200.

Check chassis airflow, 250 W power budget, CPU 8-pin auxiliary power support, physical dual-slot clearance and driver/software compatibility.

Need verified availability or a formal quote?

Send us the part number, target quantity and destination. We will confirm stock, packaging condition, lead time and current promotional pricing.