AMD Instinct MI100 32GB
CDNA PCIe 2020 7nm
FP32
23.1
TFLOPS
VRAM
32 GB
HBM2
TDP
300 W
77.0 TFLOPS/kW
Bandwidth
1.2 TB/s
memory
Performance Metrics
Peak theoretical throughput by precision type
| Precision | Description | Bits | Peak TFLOPS | Efficiency |
|---|---|---|---|---|
| INT8 | 8-bit integer | 8 | 184.6 | 0.615 TFLOPS/W |
| INT4 | 4-bit integer | 4 | 184.6 | 0.615 TFLOPS/W |
| FP16 | 16-bit floating point | 16 | 184.6 | 0.615 TFLOPS/W |
| BF16 | Brain Float 16 | 16 | 92.3 | 0.308 TFLOPS/W |
| FP32 | 32-bit floating point | 32 | 23.1 | 0.077 TFLOPS/W |
| FP64 | 64-bit floating point | 64 | 11.5 | 0.038 TFLOPS/W |
FP16 Efficiency
0.615 TFLOPS/W
184.6 TFLOPS / 300W
FP32 Efficiency
0.077 TFLOPS/W
23.1 TFLOPS / 300W
Power Specifications
TDP
300 W
Max Power
345 W
Power Connector
PCIe 8-pin
Cooling
Air
Memory Specifications
Capacity
32 GB
Type
HBM2
Bandwidth
1228.8 GB/s
Interface
--
Hardware & Design
Form Factor
PCIe
Architecture
CDNA
Process Node
7nm
Launch Year
2020
Variant
32GB
Market Segment
Data Center
Common Use Cases
General Compute AI/ML Workloads Data Processing
The AMD Instinct MI100 is optimized for high-performance computing tasks with CDNA architecture delivering 23.1 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 ProvidersStay Updated on GPU Releases
Get notified when new GPUs are added or specifications are updated.
Loading verification...
No spam, unsubscribe anytime.