Skip to content
NVNEXUS
info@nvnexus.com
Talk to an Expert →
GPU Comparison

NVIDIA A100 80GB vs AMD Instinct MI350X

How the NVIDIA A100 80GB and AMD Instinct MI350X compare across memory, compute, power and form factor, with the stronger figure highlighted on each row. Vendor-specific figures (CUDA vs stream processors, Tensor vs matrix cores) are listed on their own rows.

Specification NVIDIA A100 80GB AMPERE NVIDIA A100 80GB View Product → CDNA 4 AMD Instinct MI350X NVIDIA alternative: NVIDIA B200 →
Pricing
Price – Not sold by NVNexus
Overview
Architecture Ampere AMD CDNA 4
Memory
Memory 80 GB HBM2e 288 GB HBM3E
Memory Bandwidth 2,039 GB/s 8 TB/s
Memory Interface – 8192-bit
Compute
Stream Processors (AMD) – 16,384 (256 CUs)
Matrix Cores / AI Accelerators (AMD) – 1,024
FP32 19.5 TFLOPS 144.2 TFLOPS
FP64 Tensor 19.5 TFLOPS 72.1 TFLOPS
TF32 Tensor 312 TFLOPS (Sparse) –
FP16/BF16 Tensor 624 TFLOPS (Sparse) 2.3 PFLOPS / 4.6 (sparse) TFLOPS
FP8 Tensor – 4.6 PFLOPS / 9.2 (sparse) TFLOPS
FP4 Tensor – 9.2 PFLOPS TFLOPS
INT8 Tensor 1,248 TOPS (Sparse) –
Platform
Interface Gen4 PCIe Gen5 x16
NVLink / Infinity Fabric 600 GB/s Infinity Fabric, 1,075 GB/s aggregate
TDP 400W 1000W
Form Factor – OAM module (8-GPU platform)
Multi-Instance GPU (MIG) Up to 7 instances –
Cooling – Air cooled
Transistors – 185 billion
Not sure which fits?

Talk it through with a specialist

Tell us your workload and we will recommend the right GPU, configuration, and sourcing options.

Talk to an Expert →

More Comparisons