NVIDIA GeForce RTX 5090
VRAM
32 GB
Memory
GDDR7
Bandwidth
1,792 GB/s
FP16
419 TF
TDP
575 W
Memory and compute
Architecture and power
Notes
FP16 dense tensor with FP16 accumulate. The highest-VRAM consumer card; common self-host choice for quantized 30B-70B models.
Models that may fit on NVIDIA GeForce RTX 5090
Estimates based on INT8 quantization. Actual fit depends on framework and batch size.
More GPUs by NVIDIA
The manufacturer's other cards in the catalog, largest memory first, with bandwidth and power where published.
Frequently asked questions about NVIDIA GeForce RTX 5090
Answered from the entry's own figures: memory, which models fit, bandwidth, power and the card's class.
NVIDIA GeForce RTX 5090 has 32 GB of GDDR7 at 1,792 GB/s. At INT8 a model's weights take about one byte per parameter, so the card holds roughly a 25B-parameter model with room for context; larger models need several cards or a lower precision.
From the catalog's estimates at INT8, Qwen 2.5 14B Instruct, Llama Nemotron Embed VL 1B V2, GLM Z1 9B 0414 and NVIDIA Nemotron Nano 12B V2 VL BF16 fit on a single NVIDIA GeForce RTX 5090 with their default context. The list on this page shows the estimated memory each takes; the capacity planner sizes any model against this card for your own context length, batch size and request rate.
1,792 GB/s. Bandwidth bounds how fast a model generates tokens, because every token reads the whole set of weights and the KV cache from memory; at this rate a 25B model at INT8 could be read on the order of 70 times a second on one card, before batching and framework efficiency.
NVIDIA GeForce RTX 5090 has a TDP of 575 W, in the PCIe form factor. Budget the TDP per card plus host overhead when sizing a server's power and cooling.
NVIDIA GeForce RTX 5090 is a consumer card from the gaming line, the lowest price per card and no inter-card link, built on the Blackwell architecture and released in 2025. It has no multi-GPU interconnect, so a model must fit on one card or be split over the slower PCIe bus.
Specifications from the manufacturer's published material; a figure that is not published is shown as such, and a derived one is explained in the notes.
Added Jul 30, 2026 · Last updated Jul 30, 2026
Explore more
Companion tools that draw on the same catalog and routing engine.
Put intelligence in the middle.
One gateway in front of every model, with your policies applied and every decision on record. Start on the free plan with 5,000 requests a month, no card required.