Spheron GPU Catalog

NVIDIA RTX 5090 GPU: 32GB GDDR7 Specs, Pricing & Rental. Rent RTX 5090 GPU from $0.92/hr

32GB GDDR7, Blackwell architecture, 5th gen Tensor Cores. RTX 5090 GPU rentals deployed in under 2 minutes.

At a glance

You can rent an NVIDIA RTX 5090 on Spheron starting at $0.92/hr per GPU per hour, the lowest live marketplace rate. Per-minute billing, no contracts, deployed in under 2 minutes across data center partners in multiple regions. The RTX 5090 packs 32GB of GDDR7 memory and 5th gen Tensor Cores, making it the best price-to-performance choice for LoRA/QLoRA fine-tuning of 7B-13B models, Stable Diffusion XL inference, local LLM serving with Ollama or vLLM, and general AI development work. Launch a container with your CUDA/PyTorch image, SSH in, and start training in minutes.

GPU ArchitectureNVIDIA Blackwell
VRAM32 GB GDDR7
Memory Bandwidth1.79 TB/s

NVIDIA RTX 5090 specifications

GPU Architecture
NVIDIA Blackwell
VRAM
32 GB GDDR7
Memory Bandwidth
1.79 TB/s
Tensor Cores
5th Generation
CUDA Cores
21,760
RT Cores
4th Generation
FP32 Performance
104.8 TFLOPS
FP16 Tensor (dense)
209.5 TFLOPS
FP8 Tensor (dense)
419 TFLOPS
INT8 Tensor (dense)
838 TOPS
FP4 Tensor (sparse)
3,352 TOPS
System RAM
24 GB DDR5
vCPUs
8 vCPUs
Storage
200 GB NVMe SSD
Network
PCIe Gen5
TDP
575W

NVIDIA RTX 5090 pricing

ProviderPrice/hrSavings
SpheronYour price
$0.92/hr-
CloudRift
$0.65/hr-
NeevCloud
$0.69/hr-
RunPod (Community)
$0.69/hr-
RunPod (Secure)
$0.99/hr1.1x more expensive
Custom & Reserved

Need More RTX 5090 Than What's Listed?

Reserved Capacity

Commit to a duration, lock in availability and better rates

Custom Clusters

8 to 512+ GPUs, specific hardware, InfiniBand configs on request

Supplier Matchmaking

Spheron sources from its certified data center network, negotiates pricing, handles setup

Need more RTX 5090 capacity? Tell us your requirements and we'll source it from our certified data center network.

Typical turnaround: 24–48 hours

When to pick the RTX 5090

Scenario 01

Pick RTX 5090 if

Your workload is LoRA/QLoRA fine-tuning on 7B-13B models, Stable Diffusion XL or Flux inference, or local LLM serving where 32GB VRAM is plenty. You want the cheapest Blackwell-generation GPU with 5th gen Tensor Cores and aren't bottlenecked by multi-GPU interconnect.

Recommended fit
Scenario 02

Pick RTX 4090 instead if

You need the absolute lowest hourly rate and 24GB VRAM is enough for your model. Your workload doesn't benefit from Blackwell's 2x AI throughput or the bandwidth jump from GDDR6X to GDDR7.

Recommended fit
Scenario 03

Pick RTX PRO 6000 instead if

You need 48GB or 96GB VRAM on Blackwell silicon to serve 30B+ quantized models on a single GPU, or you want pro-tier drivers and ECC memory for production workloads.

Recommended fit
Scenario 04

Pick H100 instead if

You're training or fine-tuning 30B+ parameter models end-to-end, need HBM3 bandwidth and NVLink/InfiniBand for multi-GPU, or your workload requires the Hopper FP8 Transformer Engine.

Recommended fit

NVIDIA RTX 5090 use cases

Use case / 01
🛠️

AI Prototyping & Development

Rapidly iterate on AI models at low cost, making the RTX 5090 ideal for development workflows and early-stage experimentation.

Model architecture experimentationRapid prototypingDevelopment and debuggingCI/CD ML pipelines
Use case / 02
🎯

Small Model Fine-Tuning

Perform LoRA and QLoRA fine-tuning of models up to 13B parameters with 32GB of fast GDDR7 memory.

Domain-specific fine-tuning (7B-13B models)Instruction tuningRLHF experimentsAdapter training
Use case / 03
💰

Cost-Effective Inference

Deploy smaller models at minimal cost for production inference workloads that demand high throughput at a budget-friendly price.

7B model inferenceChatbot deploymentImage classification APIsReal-time NLP services
Use case / 04
📚

AI Education & Research

Affordable GPU access for learning, research, and open-source contributions without the overhead of expensive data center GPUs.

ML courses and workshopsAcademic researchKaggle competitionsOpen-source model development

NVIDIA RTX 5090 benchmarks

Llama 3.1 8B Inference
~3,500 tokens/s
FP16, vLLM batched
Llama 3.1 8B (Q4_K_M)
~65 tokens/s
llama.cpp, single stream
Stable Diffusion XL
~16 img/min
1024x1024, base + refiner
Mistral 7B QLoRA
~720 tokens/s
INT4 fine-tuning
Memory Bandwidth
1,792 GB/s
GDDR7, 512-bit bus
vs RTX 4090
+28-50%
LLM tokens/s uplift

Serve Llama 3.1 8B on RTX 5090 with vLLM

Spin up an OpenAI-compatible inference endpoint on a single RTX 5090. The 32GB GDDR7 fits Llama 3.1 8B in FP16 with room for an 8K context window.

bash
Spheron
# SSH into your RTX 5090 instancessh root@<instance-ip> # Install vLLM (CUDA 12.x compatible)pip install vllm # Serve Llama 3.1 8B in FP16 on a single RTX 5090vllm serve meta-llama/Meta-Llama-3.1-8B-Instruct \  --dtype float16 \  --max-model-len 8192 \  --gpu-memory-utilization 0.9 \  --port 8000 # Test the OpenAI-compatible endpointcurl http://localhost:8000/v1/chat/completions \  -H "Content-Type: application/json" \  -d '{    "model": "meta-llama/Meta-Llama-3.1-8B-Instruct",    "messages": [{"role": "user", "content": "Hello"}]  }'

RTX 5090 vs alternatives

NVIDIA RTX 5090 guides and resources

01Technical Brief

RTX 5090 Release Date and Cloud Availability

The NVIDIA GeForce RTX 5090 launched January 30, 2025 at $1,999 MSRP. NVIDIA announced the card at CES 2025 on January 7, 2025 as the flagship of the consumer Blackwell generation, with the RTX 5090 Founders Edition and AIB partner cards shipping later that month. The mobile RTX 5090 Laptop GPU followed in March 2025.

Cloud availability followed within weeks. Smaller GPU clouds were renting RTX 5090 by February 2025, with broader provider coverage by Q2 2025. On Spheron the RTX 5090 is available on-demand at per-minute billing with no contract, deployed across data center partners in North America, Europe, and Canada. Current availability and live pricing is on the pricing page. The RTX 5090 successor, NVIDIA's next-generation consumer card, has not been announced as of mid-2026.

02Technical Brief

RTX 5090 VRAM: 32GB GDDR7 Memory and Bandwidth

The RTX 5090 ships with 32GB of GDDR7 memory on a 512-bit bus, delivering 1.79 TB/s of memory bandwidth. That is a 33% VRAM increase and roughly 78% more bandwidth than the RTX 4090's 24GB GDDR6X at 1.01 TB/s. For AI workloads, the 32GB VRAM lets the RTX 5090 hold a 7B model in FP16 with an 8K context window, a 13B model in FP8 with room for a small batch, or a 30B model in INT4 with KV cache headroom for short context generation.

Where the 32GB VRAM matters most: LoRA and QLoRA fine-tuning of 7B-13B models, Stable Diffusion XL serving with ControlNet and a half-dozen LoRA adapters loaded, local LLM serving with Ollama or vLLM for sub-13B models, and AI development environments where the previous RTX 4090's 24GB VRAM was the bottleneck. For 70B-class models the RTX 5090's VRAM is insufficient even at INT4 quantization; the H100 SXM5 with 80GB HBM3 or H200 SXM5 with 141GB HBM3e is the right step up.

FAQ / 11

NVIDIA RTX 5090 FAQ

NVIDIA RTX 5090 alternatives and related GPUs