NVIDIA RTX 5090
21,760
CUDA Cores
32GB
VRAM
3352
GB/s
Technical Specifications
21,760
CUDA Cores
1300
Base MHz
2600
Boost MHz
32GB GDDR7
512-bit bus
Performance
104
FP32 TFLOPS
208
FP16 TFLOPS
575W
TDP
Cloud Availability
2
Available Instances
$0.27/hr
Starting Price
Detailed Specifications
| Architecture | Blackwell (Unknown) |
| Release Date | 2025-01-30 |
| Launch Price | $1,999.00 |
| Process | 4nm |
| Transistors | 100B |
AI Features
Gen 5
Tensor Cores
Disabled
Transformer Engine
Not Supported
Flash Attention
Physical Specifications
Dimensions
11in
Length
4.5in
Width
3-slot
Height
About RTX 5090 GPU
The NVIDIA RTX 5090 was introduced in 2025 on the Blackwell architecture. Its specification combines 21,760 CUDA cores with 32GB of GDDR7, which defines both the workloads it can run and the batch sizes it can hold.
Based on its 32GB memory capacity, the RTX 5090 is best evaluated for model fine-tuning, production inference, image generation, and multi-GPU development. Always size the model, optimizer state, KV cache, and framework overhead together rather than choosing a GPU from core count alone.
GPUvec currently tracks 2 cloud listings for the RTX 5090, with the lowest observed hourly rate at $0.27. Prices and availability can change by provider, region, and instance configuration, so verify the final rate before starting a workload.
For software planning, the RTX 5090 combines 3,352 GB/s of memory bandwidth, CUDA compute capability 12.0, and a 4nm manufacturing process. Confirm the minimum CUDA, PyTorch, TensorFlow, or driver version required by your application before renting or purchasing hardware.
Rent RTX 5090 from Our Partners
Get started quickly with these trusted GPU cloud providers. We may earn a commission when you sign up.
External Resources
Learn more about GPUs from these authoritative sources:
Official CUDA programming guide
NVIDIA GPU Specifications →Official NVIDIA GPU specs
TechPowerUp GPU Database →Comprehensive GPU specifications
CUDA Compute Capability Guide →GPU compute capability reference
What You Need to Know About the RTX 5090
Complete Specifications for the NVIDIA RTX 5090
The NVIDIA RTX 5090 uses the Blackwell architecture and combines 21,760 CUDA cores with 32GB of GDDR7. GPUvec records 3,352 GB/s memory bandwidth alongside architecture, release date, process node, accelerator features, and physical specifications so the page can be evaluated from source data instead of model-name assumptions.
Compare NVIDIA RTX 5090 Cloud Rental Prices per Hour
GPUvec currently tracks 2 cloud listings, with an observed starting rate of $0.27 per hour. Provider rates can vary by region, host configuration, billing model, and availability. Use the provider directory and related-GPU links to compare an available alternative when this exact accelerator is not listed.
Is the NVIDIA RTX 5090 the Right GPU for Your AI Workload?
Start with the 32GB memory limit, then evaluate 3,352 GB/s memory bandwidth, compute features, and software compatibility for your workload. Model weights, KV cache, activations, optimizer state, and framework overhead all consume memory. Compare this page with related accelerators rather than assuming that a higher core count alone guarantees a better training or inference result.
Top GPUs for Training and Inference
| Category | Rank 1 | Rank 2 | Rank 3 |
|---|---|---|---|
| Best for Training | NVIDIA H200 | NVIDIA H100 | NVIDIA B200 |
| Best for Inference | NVIDIA A40 | NVIDIA A100 | NVIDIA A10 |
Compare GPU specifications and cloud instances to find the best GPU for your workload.