RTX PRO 6000 WS vs Max-Q: same speed?

Both are listed with 96 GB and about 119 TFLOPS FP32. The WS runs at 600 W versus 300 W for the Max-Q, which gives more headroom to hold clocks during long, heavy jobs.

RTX PRO 6000 WS vs RTX 5090?

The RTX 5090 has 32 GB and about 107.6 TFLOPS. The RTX PRO 6000 WS triples the memory to 96 GB with about 119 TFLOPS, so it runs models and scenes that will not fit on a 5090.

Do I need special drivers for Blackwell?

You need CUDA 12.8 or newer builds of your framework for compute capability 12.0. Check the CUDA and framework versions in your template or Docker image before you deploy.

What happens to billing when I stop the server?

A stopped instance is charged for storage only, and the GPU is released, so starting again may wait until it is free. Destroy it once your checkpoints and outputs are saved and charges stop.

GPU Cloud · NVIDIA · Blackwell

Rent an NVIDIA RTX PRO 6000 WS GPU with 96 GB VRAM

Name: NVIDIA RTX PRO 6000 WS cloud GPU
Brand: Cloudj
Availability: InStock

Rent RTX PRO 6000 WS cloud GPU servers by the hour on Cloudj: 96 GB VRAM, NVIDIA Blackwell and about 119 TFLOPS FP32, tied for the highest FP32 in our GPU list. The 600 W workstation edition suits AI teams and studios that want 96 GB for 70B-class models plus top-end compute for rendering, video and training. Use CUDA 12.8 or newer builds of your software, pick a live configuration and connect over SSH with your key.

Rent RTX PRO 6000 WS All GPUs

RTX PRO 6000 WS specifications

VRAM per GPU

96 GB

Architecture

NVIDIA Blackwell

Compute capability

FP32 compute

≈ 119 TFLOPS

Memory bandwidth

≈ 1403 GB/s

Power limit

600 W

Values reported by the infrastructure provider for machines currently listed; real performance varies by machine.

Live RTX PRO 6000 WS configurations and prices

From $1.70/h

incl. 32 GB disk · Live price, updated every 15 minutes

Deploy

What you can run on the RTX PRO 6000 WS cloud GPU

70B models on one GPU

Serve 70B at 8-bit or 4-bit with a very large KV cache, no multi-GPU setup required.

Fast rendering and simulation

119 TFLOPS FP32 at 600 W, tied with the Max-Q for the highest FP32 listed, drives path tracing and GPU simulation.

Fine-tuning 30B–70B models

Run LoRA on 30B-class models in BF16 or QLoRA on 70B with long sequences.

Generative video pipelines

Keep video, image and text models loaded together in 96 GB for end-to-end ComfyUI workflows.

Is the RTX PRO 6000 WS the right GPU for your workload?

Choose the RTX PRO 6000 WS when your workloads require 96 GB of VRAM and Blackwell architecture features without moving to datacenter-segment hardware. If your models require less memory, a consumer or smaller workstation GPU is more economical, while extreme-scale training jobs may require a datacenter-class GPU with higher memory bandwidth.

RTX PRO 6000 WS vs similar cloud GPUs

GPU	VRAM per GPU	FP32 compute	Power limit
NVIDIA RTX PRO 6000 WS	96 GB	≈ 119 TFLOPS	600 W
NVIDIA RTX PRO 6000 Max-Q	96 GB	≈ 119 TFLOPS	300 W	Details →
NVIDIA RTX PRO 6000 S	96 GB	≈ 93.6 TFLOPS	600 W	Details →
NVIDIA RTX 6000D	84 GB	≈ 77.6 TFLOPS	600 W	Details →
NVIDIA RTX 6000Ada	48 GB	≈ 81.4 TFLOPS	300 W	Details →

Guides for RTX PRO 6000 WS

RTX PRO 6000 cloud: renting 96 GB Blackwell GPUs by regionA guide to RTX PRO 6000 cloud rentals: the Workstation, Max-Q and Server variants, what 96 GB on one card enables, region searches and Blackwell driver checks.Text to video GPU cloud guide: VRAM, disk and region choicesPlan a text to video GPU cloud setup in the right order: VRAM tier first, then disk size, then region and bandwidth price for large video downloads.Run 70B LLM GPU setups in the cloud: VRAM math and EU optionsWork out how much VRAM you need to run 70B LLM GPU setups, compare 2x 48 GB, one 80 to 96 GB card and 4x 24 GB, and search EU hosts that fit.GPU cloud Asia guide: Japan, Singapore, Korea and nearbyA practical GPU cloud Asia guide: which country codes to search for East and Southeast Asian users, a fallback order, and how to pair a GPU with a VPS.

All articles →

RTX PRO 6000 WS cloud GPU: frequently asked questions

Rent the RTX PRO 6000 WS cloud GPU by the hour

Pick a live configuration, choose a template and connect over SSH with your key. Billing stops when you destroy the instance.

Rent RTX PRO 6000 WS All GPUs