DRACO 4× RTX PRO 6000 Blackwell AI Workstation

Overview

The DRACO 4× RTX PRO 6000 Blackwell AI Workstation is RDP’s flagship desk-side AI machine — four NVIDIA RTX PRO 6000 Blackwell GPUs and a full 384 GB of next-generation GDDR7 GPU memory in a single quiet, liquid-cooled tower, engineered for teams that want data-centre-class fine-tuning and inference without a data centre. It puts a private, on-premises alternative to four rented top-end cloud GPUs under one desk: your models and data never leave the building, costs are fixed in INR, and the box is productive on day one.

Built for AI/ML teams, research labs and product-engineering groups standardising on a repeatable, secure local-AI platform, it balances 384 GB of aggregate GPU memory, a high-core Intel Xeon W-3500 data-prep engine, 512 GB of ECC system memory and 16 TB of NVMe — the difference between a workstation that benchmarks well and one that sustains real large-model training and serving.

Key highlights

• 384 GB of GPU memory across 4× RTX PRO 6000 Blackwell — fine-tune and serve very large models locally; run several large models at once without queueing for shared cloud capacity.
• 96 GB per GPU, Blackwell architecture with FP4 — next-gen accuracy and inference efficiency; ECC throughout for long, stable fine-tune runs.
• Intel Xeon W-3500 + 512 GB DDR5 ECC — a high-core data-prep, tokenisation and orchestration engine so the four GPUs aren’t starved.
• 16 TB NVMe + 25 GbE — fast local datasets, checkpoints and weights, with high-speed networking for multi-node scaling; no egress fees.
• Liquid-cooled, desk-side — sustained all-GPU clocks under load, quiet enough for an office, not a server room.
• On-prem data sovereignty — your IP and customer data stay in-house; DPDP-friendly, air-gappable.
• Make-in-India OEM — predictable INR pricing, GST tax invoice (HSN 8471), pan-India onsite support, GeM-procurable.
• Upgrade path — when you outgrow four desk-side GPUs or need trillion-parameter training, move to an RDP rack-scale GPU server / NVL-class system.

AI workload fit (what it actually runs — honestly)

• Full-precision large models: a 70B model in FP16 (~140 GB) runs comfortably; with 384 GB aggregate you can hold much larger models or several in parallel, tensor-parallel across all four cards.
• Inference: serve 70B–180B-class models (quantised for the largest), or run multiple full-precision mid-size models concurrently across the four GPUs.
• Fine-tuning: QLoRA / LoRA up to ~180B, and full fine-tuning of up to ~13B models, data-parallel across the four GPUs.
• Vision, multimodal, RAG & agentic: train/serve vision and multimodal models, build RAG pipelines on the 16 TB NVMe, and run multi-agent workflows locally.
• Engineering note: the RTX PRO 6000 Blackwell workstation card has no NVLink, so the four cards run over PCIe — use tensor parallelism for a single model larger than 96 GB and data parallelism for multi-model serving. This is the right tool for large-model fine-tuning + inference at team scale, not 1000-GPU pre-training.

AI workload positioning

This sits at the fine-tune-and-deploy stage of the AI lifecycle, at the very top of what a desk-side workstation can do: lighter and far cheaper to own than a rack-scale cluster, but with enough GPU memory to handle 70B–180B-class models on-prem. With 384 GB of Blackwell GPU memory, a high-core Xeon W, ECC memory and fast NVMe in balance, it is built to sustain data-centre-class fine-tuning and high-throughput inference at the desk.

Industry use cases

• Manufacturing — defect-detection vision models and digital-twin simulation on the factory floor.
• Healthcare & life sciences — fine-tune medical LLMs / imaging models on-prem, keeping PHI in-house.
• BFSI — private fraud, risk and document-intelligence models under data-residency rules.
• Media & design — generative image/video and 3D/rendering pipelines.
• Research & higher-ed — a shared lab AI workstation for NLP, speech and multimodal research.
• Software / product teams — local large-model fine-tuning, eval and agentic-app development without cloud bills.

Performance — and how to be sure

We don’t publish inflated peak numbers. The honest picture: 384 GB of aggregate GPU memory and four top-end Ada-successor GPUs are sized to fine-tune up to ~180B (QLoRA) and serve 70B-class models in FP16 on-prem. Want certainty? Request a free benchmark of your model and dataset on this exact configuration before you buy — we’ll send back real tokens/sec and fine-tune timings for your workload.

Series & upgrade path

• CARINA (entry, 1× GPU) · QUASAR (performance, 2× GPU) · DRACO (flagship, 4× GPU — this, top of tier).
• GPU generation: this is the current-generation Blackwell flagship (96 GB GDDR7, FP4) — the most GPU memory available in a desk-side RDP workstation.
• When to step up: beyond four GPUs or for trillion-parameter training, move to an RDP rack-scale GPU server / NVL-class system — talk to an architect for the migration path.

On-prem vs cloud — the TCO case

For sustained fine-tuning and inference, owning beats renting: four equivalent top-end cloud GPUs running continuously add up fast, and on-prem removes egress fees and keeps data in-house. RDP pricing is fixed in INR with a GST input-credit-eligible invoice — ask for a 3-year TCO comparison against your current cloud spend.

Software & day-one readiness

Ships pre-loaded and ready to train: NVIDIA driver, CUDA, cuDNN, Docker and NVIDIA Container Toolkit, with PyTorch / TensorFlow and common inference servers (vLLM / Triton) configured on Ubuntu LTS. Optional managed AI-stack and model-zoo setup available.

Power, thermal & acoustics

Four top-end GPUs plus the Xeon W-3500 draw substantial power — specify a dedicated circuit. The system is liquid-cooled to hold full clocks quietly at the desk. (Exact PSU rating, BTU and dB(A) figures confirmed on the build sheet.)

Deployment, warranty & support

• Made to order, built and burned-in in India; realistic lead time confirmed at quote.
• In the box: workstation, power cables, rails/feet, quick-start, and the pre-installed AI software stack.
• Onsite warranty + AMC with pan-India coverage and an RMA/escalation path (exact term & response window confirmed at quote).

Why RDP

14 years of Make-in-India infrastructure and 300,000+ devices shipped. Indian OEM, INR pricing, GST tax invoice (HSN 8471), pan-India onsite engineers, GeM availability, and DPDP / sovereign-AI-ready deployment.

Buy with confidence

This is RDP’s flagship desk-side AI workstation, made to order — talk to an RDP solution architect, get a configuration and 3-year TCO tailored to your workload, and benchmark your own model on it before you commit. Request a quote to begin.

Specifications