News icon

Kimi K3 is now available on Runpod

Rent NVIDIA Pro 6000 MIG 48GB GPUs from $1.09/hr

Multi-Instance GPU (MIG) partition of the NVIDIA RTX PRO 6000 Blackwell Server Edition. A fully isolated 2g.48gb instance with 48 GB of dedicated GDDR7 ECC memory, its own compute cores and cache, and guaranteed quality of service for mid-size model fine-tuning and high-throughput inference.

Pro 6000 MIG 48GB

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

Built on the same Blackwell silicon as the flagship RTX PRO 6000, bringing fifth-generation Tensor Cores and native FP4 support to a right-sized, isolated GPU instance.

Multi-Instance GPU (MIG) Partitioning

A hardware-isolated 2g.48gb slice with its own dedicated compute cores, cache, and memory, guaranteeing quality of service independent of other tenants sharing the physical card.

48GB Dedicated GDDR7 with ECC

Half of the card's 96GB memory pool, ECC-protected and fully isolated, sized for mid-size LLM fine-tuning and high-throughput inference without CPU offloading.

Fifth-Generation Tensor Cores

Partitioned Tensor Core allocation supports FP4, FP8, and FP16 precision for efficient training and inference throughput on an isolated compute instance.

Key specs at a glance.

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

Memory Bandwidth

896

GB/s

FP16 Tensor Performance

63

TFLOPS

PCIe Gen5 ×16 Bandwidth

128

GB/s

Popular use cases.

Designed for demanding workloads. Learn if this GPU fits your needs.

Inference workload illustration

Inference

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

Fine-tuning workload illustration

Fine-tuning

Train custom models on your specific datasets.

AI agents workload illustration

Agents

Build intelligent agent-based systems and workflows.

Compute-heavy workload illustration

Compute-heavy tasks

Run compute-heavy workloads like rendering and simulations.

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
896 GB/s
Feeding a dedicated 48GB memory pool for mid-size LLM fine-tuning and high-throughput inference without CPU offloading.
FP16 Tensor Performance
63 TFLOPS
Accelerating fine-tuning and inference on models up to roughly 30B parameters within an isolated compute slice.
PCIe Gen5 ×16 Bandwidth
128 GB/s
Supporting fast host-to-GPU transfers for demanding single- or dual-tenant inference deployments sharing the physical card.
"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

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/hr
Secure Cloud
$1.09/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 & 1M+ developers worldwide

Build what’s next.

Build, train, and scale AI workloads on Runpod with cloud GPUs, Serverless, and Clusters.

Star field background