NVIDIA has not announced, named or published specifications for this card. Every figure on this page comes from a Geekbench listing and a teardown reported by the press, so treat them as provisional. It is sold for the Chinese market.

NVIDIA RTX PRO 6000D 84GB

Architecture: BlackwellForm factor: PCIeReleased: 2025Spec confidence: Vendor claimed
FP32
97
TFLOPS
Memory
84 GB
GDDR7

Overview

The RTX PRO 6000D is a cut-down Blackwell workstation and server card for the Chinese market, a sibling of the RTX PRO 6000 trimmed to sit inside US export rules. NVIDIA has never announced or specified it; what is known comes from a Geekbench listing in November 2025, where the card reported itself as the RTX 6000D, and a teardown published in February 2026. It uses the same GB202 GPU with 156 of its streaming multiprocessors enabled, 19,968 CUDA cores against the full card's 24,064, and fills 28 of the board's 32 memory sites with 3 GB GDDR7 chips for 84 GB on a 448-bit bus instead of 96 GB on 512 bits. The teardown card carries a two-slot passive heatsink like the RTX PRO 6000 Server Edition. Third-party estimates put FP32 near 97 TFLOPS. Memory bandwidth, board power and every tensor-core rate remain unconfirmed, so they are left blank here. The card is available to rent by the hour from GPU marketplaces.

Performance

Peak theoretical throughput by precision type

PrecisionDense2:4 Sparse
FP64
No verified data available Structured sparsity is a tensor-core feature; this vector precision has no sparse form
FP32
32-bit floating point
97TFLOPS Structured sparsity is a tensor-core feature; this vector precision has no sparse form
TF32
No verified data available The part supports 2:4 sparsity, but the vendor publishes no sparse figure for this precision
BF16
No verified data available The part supports 2:4 sparsity, but the vendor publishes no sparse figure for this precision
FP16
No verified data available The part supports 2:4 sparsity, but the vendor publishes no sparse figure for this precision
FP8
No verified data available The part supports 2:4 sparsity, but the vendor publishes no sparse figure for this precision
FP6
No verified data available The part supports 2:4 sparsity, but the vendor publishes no sparse figure for this precision
FP4
No verified data available The part supports 2:4 sparsity, but the vendor publishes no sparse figure for this precision
INT8
No verified data available The part supports 2:4 sparsity, but the vendor publishes no sparse figure for this precision

Specifications

Architecture

Blackwell

Form Factor

PCIe

Launch Year

2025

Process Node

No verified data available

Memory

84 GB GDDR7

Bandwidth

No verified data available

TDP

No verified data available

Max power

No verified data available

CUDA Cores

19,968

Spec Confidence

Vendor claimed

Full Specifications

Compute Engine
CUDA Cores 19,968
Streaming Multiprocessors 156
Memory
Memory 84 GB
Memory Type GDDR7
Bandwidth No verified data available
Interface Width 448-bit
Power & Thermal
TDP No verified data available
Max power No verified data available
Cooling Passive
Enterprise Features
Sparsity Yes
Physical & Media
Width 2-slot
General
Form Factor PCIe
Architecture Blackwell
Process Node No verified data available
Launch Year 2025

Datasheet & Resources

Data Provenance

Every figure traced to a source

Primary Source

Publisher
NVIDIA
Published
2026-02-12

Data Quality

Spec confidence
Vendor claimed
Clock basis
Boost
Core precisions with figures
1 of 9
Normalization
All values in TFLOPS

Rent this GPU

$1.07 / GPU-hr

Lowest of 1 live listing across 1 provider

See all rental prices →

Price history and every provider on the pricing page. Some links are affiliate links.

Similar GPUs

Frequently Asked Questions

How many TFLOPS does the NVIDIA RTX PRO 6000D have?

The NVIDIA RTX PRO 6000D delivers 97 TFLOPS FP32 at peak. Flopper does not currently have verified FP16 and FP8 throughput figures for it.

What is the power consumption of the NVIDIA RTX PRO 6000D?

Flopper does not currently have a verified TDP (Thermal Design Power) figure for the NVIDIA RTX PRO 6000D.

How much memory does the NVIDIA RTX PRO 6000D have?

The NVIDIA RTX PRO 6000D is equipped with 84 GB of memory. Flopper does not currently have a verified memory bandwidth figure for it.

What architecture is the NVIDIA RTX PRO 6000D based on?

The NVIDIA RTX PRO 6000D is based on the Blackwell architecture, launched in 2025.

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

© 2026 Flopper.io - Compare the GPUs Powering AI