AMD Instinct MI325X OAM

Official
CDNA 3 OAM 2025 5nm FinFET
FP32
163.4
TFLOPS
VRAM
256 GB
TDP
1.0 kW
163.4 TFLOPS/kW
Bandwidth
6.0 TB/s
memory
View Providers

Performance Metrics

Peak theoretical throughput by precision type

PrecisionPeak TFLOPSEfficiency
INT8 2614.9 2.615 TFLOPS/W
FP8 2614.9 2.615 TFLOPS/W
FP16 1307.4 1.307 TFLOPS/W
BF16 1307.4 1.307 TFLOPS/W
TF32 653.7 0.654 TFLOPS/W
FP32 163.4 0.163 TFLOPS/W
FP64 81.7 0.082 TFLOPS/W
FP8 Efficiency
2.615 TFLOPS/W
2614.9 TFLOPS / 1000W
FP16 Efficiency
1.307 TFLOPS/W
1307.4 TFLOPS / 1000W
FP32 Efficiency
0.163 TFLOPS/W
163.4 TFLOPS / 1000W

Power Specifications

TDP

1.0 kW

Max Power

1.1 kW

Power Connector

PCIe 16-pin

Cooling

Air

Memory Specifications

Capacity

256 GB

Type

--

Bandwidth

6000 GB/s

Interface

--

Hardware & Design

Form Factor

OAM

Architecture

CDNA 3

Process Node

5nm FinFET

Launch Year

2025

Variant

OAM

Market Segment

Data Center

Common Use Cases

General Compute AI/ML Workloads Data Processing

The AMD Instinct MI325X is optimized for high-performance computing tasks with CDNA 3 architecture delivering 163.4 TFLOPS of compute power.

Where to Rent

Compare cloud providers offering on-demand GPU instances for AI training, inference, and HPC workloads.

Browse GPU Cloud Providers

Similar GPUs

AMD Instinct MI300A 128GB

APU SH5 socket · 2023
FP32: 122.6 TFLOPS
Compare vs Instinct MI300A

Stay Updated on GPU Releases

Get notified when new GPUs are added or specifications are updated.

Loading verification...

No spam, unsubscribe anytime.

Back to GPUs