Same silicon and same 96 GB frame buffer as the RTX PRO 6000 Blackwell Workstation Edition, cut to a 300 W board power instead of 600 W. NVIDIA does that with clock rather than with cores: identical 188 SMs and 24,064 CUDA cores, boost clock 2,280 MHz against 2,617 MHz. The result is 87 percent of the full card's throughput on half the power, which is the whole point of the part.

NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition

Blackwell PCIe 2025 4nm Spec confidence: Official
FP8 (dense)
878
TFLOPS
FP32
110
TFLOPS
VRAM
96 GB
GDDR7
Bandwidth
1.8 TB/s
memory
TDP
300 W
365.7 TFLOPS/kW

Overview

The NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition is the 300 W member of the RTX PRO 6000 family. It carries the full GB202 configuration used by the 600 W Workstation Edition, 188 streaming multiprocessors, 24,064 CUDA cores, 752 fifth-generation Tensor cores and 188 fourth-generation RT cores, together with 96 GB of GDDR7 with ECC on a 512-bit bus at 1,792 GB/s. The only lever NVIDIA pulls is clock: 2,280 MHz boost instead of 2,617 MHz, which lands 109.7 TFLOPS of FP32 and 1,755.7 dense TFLOPS of FP4 against 126.0 and 2,015.2 on the full card. For anyone building a multi-GPU workstation, that trade is usually the right one, because two Max-Q cards fit the power and thermal budget of one 600 W card and bring 192 GB of memory with them. It supports Multi-Instance GPU, so a single board partitions into up to four isolated 24 GB instances. Being a professional Blackwell part it exposes the full tensor ladder, FP4 through TF32, with structured sparsity available on every rung.

Performance

Peak theoretical throughput by precision type

PrecisionDense2:4 Sparse
FP64
64-bit floating point
1.7TFLOPS Structured sparsity is a tensor-core feature; this vector precision has no sparse form
FP32
32-bit floating point
110TFLOPS Structured sparsity is a tensor-core feature; this vector precision has no sparse form
TF32
TensorFloat-32
220TFLOPS 439TFLOPS
BF16
Brain Float 16
439TFLOPS 878TFLOPS
FP16
16-bit floating point
439TFLOPS 878TFLOPS
FP8
8-bit floating point
878TFLOPS 1,756TFLOPS
FP6
No verified data available The part supports 2:4 sparsity, but the vendor publishes no sparse figure for this precision
FP4
4-bit floating point
1,756TFLOPS 3,511TFLOPS
INT8
8-bit integer
878TOPS 1,756TOPS

The RTX PRO 6000 Blackwell Max-Q Workstation Edition in the GPU landscape

Peak FP16 TFLOPS (dense) against TDP, single-GPU parts tracked by Flopper

06001,2001,8002,4003,0000 W250 W500 W750 W1000 W1250 W1500 WInstinct MI355XRTX PRO 6000 Blackwell Max-Q Workstation Edition

Higher and further left is better: more half-precision throughput for less power.

Specifications

Architecture

Blackwell

Form Factor

PCIe

Launch Year

2025

Process Node

4nm

Memory

96 GB GDDR7

Bandwidth

1,792 GB/s

TDP

300 W

Max Power

300 W

Transistors

92.2 billion

CUDA Cores

24,064

Spec Confidence

Official

Full Specifications

Compute Engine
CUDA Cores 24,064
Tensor Cores 752 (5th Gen)
Streaming Multiprocessors 188
Boost Clock 2.28 GHz
Chip Design
Transistors 92.2 billion
Die Size 750 mm²
Process Node 4nm
Memory
VRAM 96 GB
Memory Type GDDR7
Bandwidth 1.8 TB/s
Interface Width 512-bit
Memory Clock 28 GT/s
Interconnect & I/O
PCIe 5.0 x16
Cache
L2 Cache 128 MB
Power & Thermal
TDP 300 W
Max Board Power 300 W
Power Connector 1x PCIe CEM5 16-pin
Cooling Active
Enterprise Features
ECC Memory Yes
MIG Support Up to 4x 24GB, Up to 2x 48GB, Up to 1x 96GB
Sparsity Yes
Compute APIs CUDA 12.8, OpenCL 3.0, DirectCompute
Physical & Media
Card Length 266.7 mm
Width 2-slot
NVENC Engines 4
NVDEC Engines 4
General
Form Factor PCIe
Architecture Blackwell
Process Node 4nm
Launch Year 2025

Datasheet & Resources

Data Provenance

Every figure traced to a source

Primary Source

Publisher
NVIDIA
Published
2026-06-01

Data Quality

Spec confidence
Official
Clock basis
Boost
Core precisions with figures
8 of 9
Normalization
All values in TFLOPS

Rent this GPU

$0.50 / GPU-hr

Lowest of 3 live listings across 2 providers· median $1.02

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 6000 Blackwell have?

The NVIDIA RTX PRO 6000 Blackwell delivers 110 TFLOPS FP32, 439 TFLOPS FP16 and 878 TFLOPS FP8 at peak.

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

The NVIDIA RTX PRO 6000 Blackwell has a TDP (Thermal Design Power) rating of 300 watts.

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

The NVIDIA RTX PRO 6000 Blackwell is equipped with 96 GB of VRAM with 1,792 GB/s of memory bandwidth.

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

The NVIDIA RTX PRO 6000 Blackwell 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