NVIDIA GeForce RTX 5090 32GB
Performance
Peak theoretical throughput by precision type
| Precision | Dense | 2:4 Sparse |
|---|---|---|
FP64 64-bit floating point | 1.6TFLOPS | Structured sparsity is a tensor-core feature; this vector precision has no sparse form |
FP32 32-bit floating point | 105TFLOPS | Structured sparsity is a tensor-core feature; this vector precision has no sparse form |
TF32 TensorFloat-32 | 105TFLOPS | 210TFLOPS |
BF16 Brain Float 16 | 210TFLOPS | 419TFLOPS |
FP16 16-bit floating point | 419TFLOPS | The part supports 2:4 sparsity, but the vendor publishes no sparse figure for this precision |
FP8 8-bit floating point | 838TFLOPS | The part supports 2:4 sparsity, but the vendor publishes no sparse figure for this precision |
FP6 | No verified data available | The part supports 2:4 sparsity, but the vendor publishes no sparse figure for this precision |
FP4 4-bit floating point | 1,676TFLOPS | The part supports 2:4 sparsity, but the vendor publishes no sparse figure for this precision |
INT8 8-bit integer | 838TOPS | The part supports 2:4 sparsity, but the vendor publishes no sparse figure for this precision |
Dense peak divided by accelerator TDP. Board power only: excludes host CPUs, networking, cooling and facility overhead. TDP for this part: 575 W.
The GeForce RTX 5090 32GB in the GPU landscape
Peak FP16 TFLOPS (dense) against TDP, single-GPU parts tracked by Flopper
Higher and further left is better: more half-precision throughput for less power.
Specifications
Architecture
Blackwell
Form Factor
PCIe
Launch Year
2025
Process Node
4nm
Memory
32 GB GDDR7
Bandwidth
1,792 GB/s
TDP
575 W
Max power (Flopper estimate)
~661 W est. Flopper estimate: 575 W TDP x 1.15. The vendor publishes no maximum board power for this part.
Transistors
92.0 billion
CUDA Cores
21,760
Spec Confidence
Official
Full Specifications
| Compute Engine | |
|---|---|
| CUDA Cores | 21,760 |
| Tensor Cores | 680 (5th Gen) |
| Streaming Multiprocessors | 170 |
| Base Clock | 2.01 GHz |
| Boost Clock | 2.41 GHz |
| Chip Design | |
| Transistors | 92.0 billion |
| Die Size | 750 mm² |
| Process Node | 4nm |
| Memory | |
| Memory | 32 GB |
| Memory Type | GDDR7 |
| Bandwidth | 1.8 TB/s |
| Interface Width | 512-bit |
| Power & Thermal | |
| TDP | 575 W |
| Max power (Flopper estimate) | ~661 W est. |
| Enterprise Features | |
| Sparsity | Yes |
| General | |
| Form Factor | PCIe |
| Architecture | Blackwell |
| Process Node | 4nm |
| Launch Year | 2025 |
Datasheet & Resources
Flopper Datasheet
NVIDIA GeForce RTX 5090 32GB specifications, generated from our database. Printable.
Vendor product page
NVIDIA documentation for the GeForce RTX 5090 32GB
NVIDIA Developer Documentation
Technical specs, programming guides
Data Provenance
Every figure traced to a source
Primary Source
- Document
- —
- Publisher
- NVIDIA
- Published
- No verified data available
Data Quality
- Spec confidence
- Official
- Clock basis
- Boost
- Core precisions with figures
- 8 of 9
- Normalization
- All values in TFLOPS
Rent this GPU
$0.35 / GPU-hr
Lowest of 3 live listings across 2 providers· median $0.99
Median of each provider's cheapest on-demand listing, so a provider with many configurations counts once.
Price history and every provider on the pricing page. Some links are affiliate links.
Similar GPUs
NVIDIA RTX PRO 6000 Blackwell Workstation Edition
Frequently Asked Questions
How many TFLOPS does the NVIDIA GeForce RTX 5090 have?
The NVIDIA GeForce RTX 5090 delivers 105 TFLOPS FP32, 419 TFLOPS FP16 and 838 TFLOPS FP8 at peak.
What is the power consumption of the NVIDIA GeForce RTX 5090?
The NVIDIA GeForce RTX 5090 has a TDP (Thermal Design Power) rating of 575 watts.
How much memory does the NVIDIA GeForce RTX 5090 have?
The NVIDIA GeForce RTX 5090 is equipped with 32 GB of memory with 1,792 GB/s of memory bandwidth.
What architecture is the NVIDIA GeForce RTX 5090 based on?
The NVIDIA GeForce RTX 5090 is based on the Blackwell architecture, launched in 2025.
Stay Updated on GPU Releases
Get notified when new GPUs are added or specifications are updated.
No spam, unsubscribe anytime.