HU
Huawei Ascend 950PR
Da Vinci v3 OAM 2026
VRAM
128 GB
HiBL 1.0
TDP
900 W
Bandwidth
1.6 TB/s
memory
Performance Metrics
Peak theoretical throughput by precision type
| Precision | Bits | Peak TFLOPS | Efficiency |
|---|---|---|---|
| FP8 | 8 | 1000.0 | 1.111 TFLOPS/W |
| FP4 | 4 | 2000.0 | 2.222 TFLOPS/W |
| FP16 | 16 | 500.0 | 0.556 TFLOPS/W |
| BF16 | 16 | 500.0 | 0.556 TFLOPS/W |
FP8 Efficiency
1.111 TFLOPS/W
1000.0 TFLOPS / 900W
FP16 Efficiency
0.556 TFLOPS/W
500.0 TFLOPS / 900W
Power Specifications
TDP
900 W
Max Power
1.0 kW
Power Connector
PCIe 16-pin
Cooling
Air
Memory Specifications
Capacity
128 GB
Type
HiBL 1.0
Bandwidth
1600 GB/s
Interface
--
Hardware & Design
Form Factor
OAM
Architecture
Da Vinci v3
Process Node
--
Launch Year
2026
Variant
Standard
Market Segment
Data Center
Full Specifications
| Memory | |
|---|---|
| VRAM | 128 GB |
| Memory Type | HiBL 1.0 |
| Bandwidth | 1.6 TB/s |
| Interconnect & I/O | |
| GPU-to-GPU | Unified Bus 2.0 |
| Interconnect Bandwidth | 2.0 TB/s |
| Power & Thermal | |
| TDP | 900 W |
| General | |
| Form Factor | OAM |
| Architecture | Da Vinci v3 |
| Launch Year | 2026 |
Documentation & Resources
Common Use Cases
General Compute AI/ML Workloads Data Processing
The Huawei Ascend 950PR is optimized for high-performance computing tasks with Da Vinci v3 architecture delivering high 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.