Announcing Runpod Flash

Cloud GPUs

Rent NVIDIA RTX Pro 6000 GPUs from $2.09/hr

Flagship Blackwell workstation GPU with 96 GB of ECC GDDR7 memory, 24,064 CUDA cores, and massive bandwidth for frontier-scale AI, complex 3D scenes, and large simulation workloads.

RTX Pro 6000

Powering the next generation of AI & high-performance computing.

Engineered for large-scale AI training, deep learning, and high-performance workloads, delivering unprecedented compute power and efficiency.

NVIDIA Blackwell Architecture

Advanced tensor cores with FP4, FP8, and FP16 support that significantly speed up training and inference for modern AI models, from LLMs and diffusion to complex vision systems.

Fifth-generation Tensor Cores

Advanced tensor cores with FP4, FP8, and FP16 support that significantly speed up training and inference for modern AI models, from LLMs and diffusion to complex vision systems.

96 GB GDDR7 with ECC

Huge, error-corrected memory pool with very high GDDR7 bandwidth, designed for fitting larger models, longer contexts, and denser scenes on a single GPU without sharding.

Fourth-generation RT Cores

Improved ray-tracing hardware that enables more realistic lighting, faster path tracing, and fluid real-time visualization for design, media, and simulation teams.

Performance

Key specs at a glance.

Performance benchmarks that push AI, ML, and HPC workloads further.

Memory Bandwidth

1792

GB/s

FP16 Tensor Performance

126

TFLOPS

PCIe Gen5 ×16 Bandwidth

128

GB/s

Use Cases

Popular use cases.

Designed for demanding workloads
—learn if this GPU fits your needs.

Inference

Serve inference for image, text, and audio generation at any scale.

Inference

Fine-tuning

Train custom models on
your specific datasets.

Fine-tuning

Agents

Build intelligent agent-based systems and workflows.

Agents

Compute-heavy tasks

Run compute-heavy workloads like rendering and simulations.

Compute-heavy tasks

Technical Specs

Ready for your most
demanding workloads.

Essential technical specifications to help you choose the right GPU for your workload.

Specification
Details
Great for...
Memory Bandwidth
1792 GB/s
Feeding very large multi-GB datasets, long-sequence models, and complex 3D scenes into GPU memory without bottlenecks, even when everything lives on a single card.
FP16 Tensor Performance
126 TFLOPS
Accelerating high-throughput AI training and inference for LLMs, diffusion models, and computer vision pipelines that need strong FP8 and FP16 tensor performance.
PCIe Gen5 ×16 Bandwidth
128 GB/s
Streaming data from storage or CPU to the GPU at PCIe Gen5 speeds, ideal for multi-GPU rigs, fast dataset iteration, and real-time analytics or rendering pipelines.
AI Apps
Research
LLM Inference
Model Training
"The Runpod team has clearly prioritized the developer experience to create an elegant solution that enables individuals to rapidly develop custom AI apps or integrations while also paving the way for organizations to truly deliver on the promise of AI."

Amjad Masad

"Runpod is the only place I can deploy high-end GPU models instantly—no sales calls, no rate limits, no nonsense."

Daniel Chang

“The main value proposition for us was the flexibility Runpod offered. We were able to scale up effortlessly to meet the demand at launch.”

Josh Payne

“Runpod helped us scale the part of our platform that drives creation. That’s what fuels the rest—image generation, sharing, remixing. It starts with training.”

Matty Shimura

Comparison

Powerful GPUs. Globally available.
Reliability you can trust.

30+ GPUs, 31 regions, instant scale. Fine-tune or go full Skynet—we’ve got you.

Community Cloud
$1.69/hr
Secure Cloud
$2.09/hr
Unique GPU Models
Community Cloud
25
Secure Cloud
19
Global Regions
Community Cloud
17
Secure Cloud
14
Network Storage
Community Cloud
Secure Cloud
Enterprise-Grade Reliability
Community Cloud
Secure Cloud
Savings Plans
Community Cloud
Secure Cloud
24/7 Support
Community Cloud
Secure Cloud
Delightful Dev Experience
Community Cloud
Secure Cloud

10,100,100,100

Requests since launch & 400k developers worldwide

Build what’s next.

The most cost-effective platform for building, training, and scaling machine learning models—ready when you are.