NVIDIA GeForce RTX 5080 16GB
Blackwell PCIe 2025 4nm
FP32
56.3
TFLOPS
VRAM
16 GB
GDDR7
TDP
360 W
156.4 TFLOPS/kW
Bandwidth
960 GB/s
memory
CUDA Cores
10,752
336 tensor cores
Performance Metrics
Peak theoretical throughput by precision type
| Precision | Description | Bits | Peak TFLOPS | Efficiency |
|---|---|---|---|---|
| INT8 | 8-bit integer | 8 | 450.2 | 1.251 TFLOPS/W |
| FP8 | 8-bit floating point | 8 | 450.2 | 1.251 TFLOPS/W |
| FP4 | 4-bit floating point | 4 | 900.5 | 2.501 TFLOPS/W |
| FP16 | 16-bit floating point | 16 | 225.1 | 0.625 TFLOPS/W |
| BF16 | Brain Float 16 | 16 | 225.1 | 0.625 TFLOPS/W |
| TF32 | TensorFloat-32 | 32 | 112.6 | 0.313 TFLOPS/W |
| FP32 | 32-bit floating point | 32 | 56.3 | 0.156 TFLOPS/W |
| FP64 | 64-bit floating point | 64 | 0.9 | 0.002 TFLOPS/W |
FP8 Efficiency
1.251 TFLOPS/W
450.2 TFLOPS / 360W
FP16 Efficiency
0.625 TFLOPS/W
225.1 TFLOPS / 360W
FP32 Efficiency
0.156 TFLOPS/W
56.3 TFLOPS / 360W
Power Specifications
TDP
360 W
Max Power
414 W
Power Connector
PCIe 16-pin
Cooling
Air
Memory Specifications
Capacity
16 GB
Type
GDDR7
Bandwidth
960 GB/s
Interface
256-bit
Hardware & Design
Form Factor
PCIe
Architecture
Blackwell
Process Node
4nm
Launch Year
2025
Variant
16GB
Market Segment
Data Center
Transistors
45.6 billion
Die Size
378 mm²
Full Specifications
| Compute Engine | |
|---|---|
| CUDA Cores | 10,752 |
| Tensor Cores | 336 (5th Gen) |
| Streaming Multiprocessors | 84 |
| Base Clock | 2.29 GHz |
| Boost Clock | 2.62 GHz |
| Chip Design | |
| Transistors | 45.6 billion |
| Die Size | 378 mm² |
| Process Node | 4nm |
| Memory | |
| VRAM | 16 GB |
| Memory Type | GDDR7 |
| Bandwidth | 960 GB/s |
| Interface Width | 256-bit |
| Power & Thermal | |
| TDP | 360 W |
| General | |
| Form Factor | PCIe |
| Architecture | Blackwell |
| Launch Year | 2025 |
Common Use Cases
General Compute AI/ML Workloads Data Processing
The NVIDIA GeForce RTX 5080 is optimized for high-performance computing tasks with Blackwell architecture delivering 56.3 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
NVIDIA RTX PRO 6000 Blackwell Workstation Edition
PCIe · 2025
FP32: 125.0 TFLOPS
Compare vs RTX PRO 6000 BlackwellStay Updated on GPU Releases
Get notified when new GPUs are added or specifications are updated.
Loading verification...
No spam, unsubscribe anytime.