Skip to content
Cloudj
GPU Cloud · NVIDIA · Blackwell

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

Rent RTX PRO 6000 S cloud GPU servers by the hour on Cloudj: 96 GB VRAM on NVIDIA Blackwell, about 93.6 TFLOPS FP32 and 1396 GB/s memory bandwidth. The server edition of the RTX PRO 6000 runs at a 600 W power limit for teams that run 70B-class LLMs, fine-tuning and generative video as sustained datacenter-style jobs. Use CUDA 12.8 or newer builds of your software, pick a live configuration and connect over SSH with your key.

RTX PRO 6000 S specifications

VRAM per GPU

96 GB

Architecture

NVIDIA Blackwell

Compute capability

12

FP32 compute

≈ 93.6 TFLOPS

Memory bandwidth

≈ 1396 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 S configurations and prices

From $1.93/h

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

Deploy

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

Sustained LLM serving

96 GB fits 8-bit 70B or 4-bit 70B with large KV cache for steady API traffic.

Overnight fine-tuning runs

QLoRA on 70B-class and LoRA on 30B-class models in BF16 on one GPU with a 600 W power limit.

Batch video generation

Queue long video and image generation jobs in ComfyUI with all models resident in memory.

Large embeddings and RAG indexes

Embed big document collections and run retrieval plus generation on the same card.

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

Choose the RTX PRO 6000 S when your workloads require 96 GB of memory and Blackwell architecture features without moving to a datacenter-segment GPU. If your models fit into a smaller memory footprint, a consumer or lower-tier workstation card is more economical, whereas massive multi-node training jobs may warrant a dedicated datacenter GPU with higher memory bandwidth.

RTX PRO 6000 S vs similar cloud GPUs

GPUVRAM per GPUFP32 computePower limit
NVIDIA RTX PRO 6000 S96 GB≈ 93.6 TFLOPS600 W
NVIDIA RTX PRO 6000 Max-Q96 GB≈ 119 TFLOPS300 WDetails →
NVIDIA RTX PRO 6000 WS96 GB≈ 119 TFLOPS600 WDetails →
NVIDIA RTX 6000D84 GB≈ 77.6 TFLOPS600 WDetails →
NVIDIA RTX 6000Ada48 GB≈ 81.4 TFLOPS300 WDetails →

RTX PRO 6000 S cloud GPU: frequently asked questions

Rent the RTX PRO 6000 S 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.