EN
Enflame Yunsui T20
GCU / DTU 2.0 PCIe 2021 GlobalFoundries 12nm
FP32
33.6
TFLOPS
VRAM
32 GB
HBM2E
TDP
300 W
112.0 TFLOPS/kW
Performance Metrics
Peak theoretical throughput by precision type
| Precision | Bits | Peak TFLOPS | Efficiency |
|---|---|---|---|
| INT8 | 8 | 268.8 | 0.896 TFLOPS/W |
| FP16 | 16 | 134.4 | 0.448 TFLOPS/W |
| BF16 | 16 | 134.4 | 0.448 TFLOPS/W |
| TF32 | 32 | 134.4 | 0.448 TFLOPS/W |
| FP32 | 32 | 33.6 | 0.112 TFLOPS/W |
FP16 Efficiency
0.448 TFLOPS/W
134.4 TFLOPS / 300W
FP32 Efficiency
0.112 TFLOPS/W
33.6 TFLOPS / 300W
Power Specifications
TDP
300 W
Max Power
345 W
Power Connector
PCIe 8-pin
Cooling
Air
Memory Specifications
Capacity
32 GB
Type
HBM2E
Bandwidth
--
Interface
--
Hardware & Design
Form Factor
PCIe
Architecture
GCU / DTU 2.0
Process Node
GlobalFoundries 12nm
Launch Year
2021
Variant
Standard
Market Segment
Data Center
Full Specifications
| Memory | |
|---|---|
| VRAM | 32 GB |
| Memory Type | HBM2E |
| Interconnect & I/O | |
| GPU-to-GPU | GCU-LARE |
| Interconnect Bandwidth | 300 GB/s |
| Power & Thermal | |
| TDP | 300 W |
| General | |
| Form Factor | PCIe |
| Architecture | GCU / DTU 2.0 |
| Launch Year | 2021 |
Documentation & Resources
Common Use Cases
General Compute AI/ML Workloads Data Processing
The Enflame Yunsui T20 is optimized for high-performance computing tasks with GCU / DTU 2.0 architecture delivering 33.6 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.