NVIDIA Vera Rubin Superchip

Rubin Superchip 2026
FP32
260.0
TFLOPS
VRAM
576 GB
HBM4
Bandwidth
44.0 TB/s
memory

Performance Metrics

Peak theoretical throughput by precision type

PrecisionPeak TFLOPS
FP32_TC 800.0
FP6 35000.0
NVFP4 100000.0
INT8 500.0
FP8 35000.0
FP16 8000.0
BF16 8000.0
TF32 4000.0
FP32 260.0
FP64_TC 400.0
FP64 67.0

Power Specifications

TDP

--

Max Power

--

Power Connector

PCIe Slot

Cooling

Air

Memory Specifications

Capacity

576 GB

Type

HBM4

Bandwidth

44000 GB/s

Interface

--

Hardware & Design

Form Factor

Superchip

Architecture

Rubin

Process Node

--

Launch Year

2026

Variant

Superchip

Market Segment

Professional

Full Specifications

Memory
VRAM 576 GB
Memory Type HBM4
Bandwidth 44.0 TB/s
Interconnect & I/O
GPU-to-GPU NVLink-C2C
Interconnect Bandwidth 1.8 TB/s
Power & Thermal
Enterprise Features
Sparsity (2:4) Yes
General
Form Factor Superchip
Architecture Rubin
Launch Year 2026

Documentation & Resources

Common Use Cases

General Compute AI/ML Workloads Data Processing

The NVIDIA Vera Rubin is optimized for high-performance computing tasks with Rubin architecture delivering 260 TFLOPS of compute power.

Where to Rent

Compare cloud providers offering on-demand GPU instances for AI training, inference, and HPC workloads.

Browse GPU Cloud Providers

Similar GPUs

NVIDIA Rubin SXM

SXM · 2026
FP32: 130.0 TFLOPS
Compare vs Rubin

Stay Updated on GPU Releases

Get notified when new GPUs are added or specifications are updated.

Loading verification...

No spam, unsubscribe anytime.

Back to GPUs