Secondary Market savings on used NVIDIA A100 GPUs

The NVIDIA A100 Tensor Core GPU represents a pinnacle in GPU technology, designed specifically for accelerating artificial intelligence (AI) and high-performance computing (HPC) workloads.

Built on the NVIDIA Ampere architecture, the A100 is equipped with Tensor Cores that are tailored for matrix multiplication operations, a fundamental component of AI model training and inference. With an impressive 6,912 CUDA cores and 40 GB of high-bandwidth memory (HBM2), the A100 delivers unprecedented computational power.

Its multi-instance GPU (MIG) capability allows for efficient partitioning of the GPU into smaller instances, enabling simultaneous processing of multiple workloads.

Sell to Us Request a Quote

What our customers say about us

Customer-Focused IT Hardware

Since 1995, we've poured all of our efforts into delivering products that match our client's expectations and exceeds their price savings target.

With our huge inventory and industry-leading engineers, customers tell us they trust Alta for our reliability, custom configurations, parts responsiveness, lightning fast delivery and savings to boot.

Request a Bid

Huge Inventory

"Aisles and aisles of servers & IT equipment. Experts at what they do."

-Ryan, President, Priority Envelope

Trust & Longevity

“We trust Alta with refurbished equipment. The longevity of the product is just the same as if I had bought it from the distributor.”

-Traci Leffner, Sovran

An IT Geek's Dream

“I have visited Alta’s warehouse, and they have just about everything.. It’s kind of like an IT Geek’s Dream in there.”

- Dustin Siemers, TechFixers

NVIDIA A100 GPUs Information:

The NVIDIA A100 Tensor Core GPU delivers unprecedented acceleration at every scale, powering the world's highest-performing elastic data centers for AI, data analytics, and HPC applications. Providing up to 20X higher performance over the previous Volta™ generation, the A100 can efficiently scale up or be partitioned into seven isolated GPU instances with Multi-Instance GPU (MIG).

This creates a unified platform that dynamically adjusts to shifting workload demands. Supporting a broad range of math precisions, the A100 80GB model doubles GPU memory and offers the world’s fastest memory bandwidth at 2 terabytes per second, accelerating solutions for the largest models and datasets.

Request a Quote Today