NVIDIA GeForce RTX 5090: specs, pricing and what it can run
The strongest consumer option for local inference: 32GB of GDDR7 at 1.79 TB/s beats every previous consumer part. Licence terms restrict datacenter deployment.
Specifications
| Spec | NVIDIA GeForce RTX 5090 |
|---|---|
| Architecture | Blackwell |
| Released | 2025 |
| Memory | 32 GB GDDR7 |
| Memory bandwidth | 1,792 GB/s |
| Dense FP16 | 419 TFLOPS |
| FP8 tensor cores | Yes |
| Board power | 575 W |
| Interconnect | PCIe Gen5 (no NVLink) |
| Segment | consumer |
What fits in 32 GB
Weights only, at 85% of nominal capacity to leave room for the KV cache and activations. Long-context serving needs materially more headroom than this table implies.
| Quantisation | Largest model (weights only) |
|---|---|
| FP16 | ~14B parameters |
| FP8 / INT8 | ~29B parameters |
| 4-bit | ~58B parameters |
Rental cost
Indicative on-demand pricing runs roughly $0.40–$1.20 per GPU-hour depending on provider, region, and commitment. Spot and reserved capacity sit well below that band. These are ranges rather than quotes: street prices move week to week, so check retail + live cloud price feed before budgeting.