RTX 3090 · $0.15/hr · 24 GB VRAM · Europe on request →

GPU cloud for
European AI teams.

Rent 24 GB RTX 3090 compute from $0.15 per GPU hour. Launch through the API, connect over SSH, and request European or Frankfurt-oriented placement for the workloads that need it.

Order GPU Node → European capacity

24 GBGDDR6X VRAM
$0.15per GPU hour
Europeplacement by request
10496CUDA cores

gpu-node-01 · running LIVE

GPU Model RTX 3090 · 24 GB GDDR6X

Utilization

VRAM Used

15.4 GB / 24 GB

CUDA Cores 10,496

# API key required. Set BHK_API_KEY before launch.

$ bhk gpu launch --type rtx3090

→ instance gpu-node-01 subject to capacity confirmation

24 GB GDDR6X VRAM per node

10496 CUDA cores · Ampere

$0.15 per GPU hour · no minimum

By request capacity confirmation

Built for these workloads

LLM Inference Model Fine-tuning Stable Diffusion ComfyUI PyTorch Training TensorFlow Batch Rendering Video Encoding

European capacity

One GPU product. The right location for the job.

BHK Cloud offers European and Frankfurt-oriented RTX 3090 capacity by request. Share the workload and preferred location, then receive written confirmation of the placement and currently available capacity before ordering.

European and Frankfurt-oriented placement, subject to availability
24 GB RTX 3090 nodes for inference, fine-tuning, rendering, and batch work
SSH and API access for the same launch workflow in every confirmed placement
Clear confirmation before production deployment, including capacity and location

Confirm capacity → See cluster profiles

placement request REVIEW

GPURTX 3090 · 24 GB GDDR6X

Preferred regionEurope or Frankfurt

Starting rate$0.15 per GPU hour

Before orderPlacement and capacity confirmed

# send model, runtime, storage, and location
$ bhk capacity request --region frankfurt
→ deployment details confirmed in writing

Architecture

24 GB VRAM. Serious compute. Hourly pricing.

RTX 3090 with Ampere architecture, NVLink support, and GDDR6X memory bandwidth tuned for the throughput patterns of large-model inference and fine-tuning at 8-bit.

24 GB GDDR6X · 936 GB/s memory bandwidth
10,496 CUDA cores · 328 tensor cores (3rd gen)
NVIDIA NVLink for multi-GPU jobs
PCIe 4.0 · NVMe-backed persistent volumes
Pre-baked images: PyTorch 2.x, TF 2.x, CUDA 12.x

Order a Node → Cluster Profiles

gpu-node-01 · training LIVE

GPU Model NVIDIA RTX 3090 · Ampere

GPU Utilization

87%

VRAM Used

15.4 / 24 GB

Throughput ~420 tokens/sec · fp16 inference

Cost so far $0.043 · 26 min elapsed

# stream logs from running job
$ bhk gpu logs gpu-node-01 --follow
→ Epoch 3/50 · loss=2.089 · 87% GPU

How It Works

From key to running after confirmation.

Set an API key, launch a node, and push your first job after capacity confirmation.

Get an API Key

Launch a Node

Request an RTX 3090 with your preferred image. We confirm capacity before arranging access.

Run Your Job

SSH in, mount your BHK S3 datasets, and run. Billing starts on launch and stops on terminate to the second.

Terminate & Pay

bhk gpu terminate gpu-node-01. Billing stops. No idle charges. RTX 3090 has no minimum; premium GPUs require 10 hours. Confirm invoicing terms.

Cluster Profiles

Right-size for your workload.

From single-card experiments to multi-GPU workloads. Pricing starts at $0.15 per GPU hour; topology and availability must be confirmed for parallel jobs.

Profile	GPUs	VRAM	CUDA Cores	Ideal For	Price / hr
Single	1× RTX 3090	24 GB	10,496	Inference, fine-tuning, experiments	$0.15
Dual	2× RTX 3090	48 GB total*	20,992	Larger models, parallel inference	from $0.30
Quad Popular	4× RTX 3090	96 GB total*	41,984	Software-parallel training and inference	from $0.60
Octa	8× RTX 3090	192 GB total*	83,968	Distributed workloads with validated topology	from $1.20
Custom	16–256×	384 GB+	Scalable	Dedicated clusters, reserved capacity	Custom

*Total physical VRAM across cards is not automatically a single shared memory pool. Effective model capacity depends on framework support, interconnect topology, partitioning, and communication overhead.

Platform

Infrastructure without the overhead.

Everything a machine learning engineer needs, nothing a procurement team invented.

Pre-baked ML images

PyTorch 2.x, TensorFlow 2.x, CUDA 12.x, and cuDNN 9 ready to pull. Custom Docker images via --image flag.

Persistent NVMe volumes

Attach SSD-backed volumes that survive node restarts. Snapshot and clone between regions in one API call.

Co-located S3 storage

Stream training data directly from BHK S3 at workload-dependent throughput without paying egress between compute and storage.

SSH & REST access

Shell in directly or drive everything through the REST API. Both are first-class citizens, not afterthoughts.

Orchestration-ready

Terraform provider, Pulumi SDK, and Kubernetes CSI driver. Bring your existing infra-as-code workflow.

Encrypted at rest & in transit

AES-256 at rest, TLS 1.3 in transit. VRAM is wiped on node termination before the hardware returns to pool.

FAQ

GPU cloud, answered.

Questions we get asked before the first bhk gpu launch.

What workloads run well on the RTX 3090?

The RTX 3090's 24 GB VRAM is useful for LLM inference when the complete model, KV cache, concurrency, and runtime overhead fit in memory. Some roughly 30B-class models can fit with aggressive 4-bit quantization, depending on architecture and context. It is also useful for image generation, LoRA or QLoRA fine-tuning, rendering, and video processing.

How does hourly GPU billing work?

You are billed for every hour your GPU node is running, pro-rated to the second. RTX 3090 has no minimum; premium GPUs require at least 10 hours. Run a single experiment on RTX 3090 and terminate when done. Billing stops the moment you call bhk gpu terminate or terminate via the dashboard.

How fast is GPU provisioning?

Capacity and placement are confirmed before fulfillment. Ask our team about image options and setup for your workload.

Can I request European or Frankfurt GPU placement?

Yes. European and Frankfurt-oriented RTX 3090 capacity is available by request. Send the preferred location, model, expected runtime, and storage needs. We confirm the exact placement and currently available capacity in writing before you order, especially for production workloads.

Can I use my own Docker image?

Yes. BHK GPU nodes support custom Docker images via bhk gpu launch --image docker.io/yourrepo/yourimage:tag. The image is pulled and cached at the region edge. Private registries are supported with credential injection through the API.

Do you support multi-GPU jobs?

Yes. Nodes are available in 1×, 2×, 4×, and 8× RTX 3090 configurations. For distributed training across multiple nodes, use the Quad or Octa profiles with NVLink-bridged inter-GPU bandwidth. Larger clusters are available via the enterprise plan.

How is storage connected to GPU nodes?

GPU nodes and BHK S3 buckets are co-located on the same internal network. Direct intra-cluster transfers run at workload-dependent throughput with no egress fees. You can also attach persistent NVMe volumes for checkpoint storage that survive node restarts.

Do you also offer H100, H200, B200, B300 or RTX PRO 6000 SE GPUs?

Yes. Alongside the RTX 3090 fleet, BHK Cloud rents NVIDIA datacenter and professional GPUs by the GPU hour: H100, H200, B200, B300 and RTX PRO 6000 SE at current live rates when available, in USD, with a 10-hour minimum per model and hourly billing after that. Region, bundle size and capacity are confirmed before fulfillment. See the premium GPU options or ask for a quote on a full month or multi GPU booking.

Premium GPU

Need more than 24 GB of VRAM?

Beyond the RTX 3090 fleet we rent NVIDIA datacenter and professional GPUs by the GPU hour: H100, H200, B200, B300 and RTX PRO 6000 SE. Billing is hourly in USD with a 10-hour minimum per model, no setup fee and no long term commitment. Regions and bundle sizes vary by model. Review the current live rate when available; our team confirms capacity and placement before fulfillment.

NVIDIA H100

80 GB HBM3 per GPU