AMD MI250X 128GB
Official
CDNA 2 OAM 2021 6nm
FP32
47.9
TFLOPS
VRAM
128 GB
TDP
560 W
85.5 TFLOPS/kW
Bandwidth
3.3 TB/s
memory
Performance Metrics
Peak theoretical throughput by precision type
| Precision | Peak TFLOPS | Efficiency |
|---|---|---|
| INT8 | 383.0 | 0.684 TFLOPS/W |
| INT4 | 383.0 | 0.684 TFLOPS/W |
| FP16 | 383.0 | 0.684 TFLOPS/W |
| BF16 | 383.0 | 0.684 TFLOPS/W |
| FP32 | 47.9 | 0.086 TFLOPS/W |
| FP64 | 47.9 | 0.086 TFLOPS/W |
FP16 Efficiency
0.684 TFLOPS/W
383.0 TFLOPS / 560W
FP32 Efficiency
0.086 TFLOPS/W
47.9 TFLOPS / 560W
Power Specifications
TDP
560 W
Max Power
644 W
Power Connector
PCIe 16-pin
Cooling
Air
Memory Specifications
Capacity
128 GB
Type
--
Bandwidth
3277 GB/s
Interface
--
Hardware & Design
Form Factor
OAM
Architecture
CDNA 2
Process Node
6nm
Launch Year
2021
Variant
128GB
Market Segment
Data Center
Documentation & Resources
Common Use Cases
HPC Computing Scientific Simulation AI Training Data Analytics
The AMD MI250X is optimized for high-performance computing tasks with CDNA 2 architecture delivering 47.9 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 ProvidersSimilar GPUs
Stay Updated on GPU Releases
Get notified when new GPUs are added or specifications are updated.
Loading verification...
No spam, unsubscribe anytime.