NVIDIA · Q4 2023

RTX PRO 6000 Blackwell Server Edition

PCIe Gen 5

The NVIDIA RTX PRO 6000 Blackwell Server Edition is a high-performance GPU designed for datacenter environments. It targets AI and data analytics workloads, leveraging the Blackwell architecture to deliver enhanced performance and efficiency. This variant is optimized for server use, offering advanced features like PCIe Gen 5 connectivity for improved data throughput.

RTX PRO 6000 Blackwell Server Edition PCIe Gen 5 — illustration of the card's form factor
VRAM
96GB
FP32 TFLOPS
120 TFLOPS
CUDA Cores
24,064
Memory
GDDR7

Provider Marketplace

Cheapest
$0.48/hour
Starting from
Best Value
$1.69/hour
Starting from
Enterprise Choice
$3.03/hour
Starting from

All Cloud Providers

14 Options available
Google Cloud logo
Google CloudCheapest
Spot · preemptible
$0.48/ hour
Estimated Cost
Provision
Verda logo
Spot · preemptible
$0.94/ hour
Estimated Cost
Provision
Nebius logo
Spot · preemptible
$0.95/ hour
Estimated Cost
Provision
CloudRift logo
Reserved · commitment
$1.10/ hour
Estimated Cost
Provision
Fal logo
On-Demand
$1.10/ hour
Estimated Cost
Provision
CoreWeave logo
Spot · preemptibleNORTH AMERICA
$1.20/ hour
Estimated Cost
Provision
Hyperstack logo
Reserved · commitment
$1.30/ hour
Estimated Cost
Provision
RunPod logo
On-Demand
$1.69/ hour
Estimated Cost
Provision
Jarvis Labs logo
On-Demand
$1.89/ hour
Estimated Cost
Provision
E2E Networks logo
On-Demand
$1.90/ hour
Estimated Cost
Provision
$2.19/ hour
Estimated Cost
Provision
Runcrate logo
On-Demand
$2.41/ hour
Estimated Cost
View Provider
Lightning AI logo
On-Demand
$2.89/ hour
Estimated Cost
Provision
Modal logo
On-Demand
$3.03/ hour
Estimated Cost
Provision

Estimates onlyrates are collected automatically from public provider pages and may be out of date. Prices vary by region, commitment term, and availability, and typically exclude storage, egress, and tax. Confirm current pricing with the provider before purchasing. Last collected .

Compute Performance

FP32120 TFLOPS
TF32234 TFLOPS
FP82 PFLOPS TFLOPS

Architecture

MicroarchitectureBlackwell
CUDA Cores24064
RT Cores4th Gen, 188 RT Cores
Matrix EngineTransformer Engine (2nd Generation)
Transformer EngineYes (2nd Gen)
Dynamic PrecisionSupported (FP4/FP8/FP16/BF16/TF32)

Memory & VRAM

Memory TypeGDDR7
Total Capacity96GB
Bandwidth1597 GB/s
Bus Width512-bit
ECC SupportYes (ECC)

Connectivity & Scaling

InterconnectPCI Express
GenerationPCIe Gen 5
PCIe InterfaceGen 5

Virtualization

MIG SupportSupported
MIG Partitions4 instances
GPU SharingMIG

Power & Efficiency

Peak Power600
Thermal LimitsAir-Cooled; Liquid-Cooled

Physical Design

Form FactorPCIe

Thermals & Cooling

Liquid CoolingSupported (liquid-cooled variant available)

Server & Deployment

OEM AvailabilityAvailable Now
PreconfiguredPartners unveil high-volume systems featuring NVIDIA RTX PRO 6000 Blackwell Server Edition GPUs to accelerate workloads from AI to IT.
Rack-ScaleThe latest 6U design supports the new liquid‑cooled NVIDIA RTX PRO 6000 Blackwell Server Edition, delivering efficient performance for next-generation AI factories.

System Compatibility

Required PCIePCIe Gen 5
Rack PowerUp to 600W (configurable)

Multi-GPU Scalability

Scaling Characteristics

ParallelismUp to four fully isolated MIG instances per GPU

Workload Readiness

LLM Inference

supported

Multimodal AI

supported

HPC / Simulation

supported

Scientific Computing

supported

Market Authority

Key Strengths

This GPU excels at AI training and inference tasks, offering significant performance improvements over previous generations. Its architecture is optimized for scientific visualization and data analytics, making it a strong choice for research institutions and enterprises needing high computational power.

Limitations

While offering cutting-edge performance, the RTX PRO 6000 Blackwell Server Edition may have higher power consumption compared to other models, requiring efficient power management. Availability might be limited initially due to high demand and production constraints, potentially impacting deployment timelines.

Expert Insight

The RTX PRO 6000 Blackwell Server Edition represents a strategic leap in AI compute. When comparing cloud providers, consider not just the hourly rate, but also the interconnect bandwidth (InfiniBand/NVLink) and regional availability which can significantly impact total cost of ownership for large-scale training.

Glossary Terms

FP32 TFLOPS
VRAM
TDP
Cores
Information updated daily. Cloud pricing subject to vendor availability.