Rent NVIDIA RTX 6000D GPU by the hour
The NVIDIA RTX 6000D is a Blackwell-architecture workstation GPU equipped with 84 GB of VRAM and compute capability 12.0. It delivers about 77.6 TFLOPS of single-precision compute and about 1222 GB/s of memory bandwidth within a 600 W power envelope. Rent this card on ONIE with per-hour billing, full SSH access, and ready templates for PyTorch/CUDA, vLLM, Ollama, and ComfyUI.
Specifications
VRAM per GPU
Architecture
Compute capability
FP32 compute
Memory bandwidth
Power limit
Values reported by the infrastructure provider for machines currently listed; real performance varies by machine.
Available configurations
Live stock and prices, updated continuously. The final price is confirmed before you order.
Loading live prices…
What the RTX 6000D is good for
Large Language Model Inference
Run substantial language models and extended context windows entirely within the 84 GB memory buffer using vLLM or Ollama.
Model Fine-Tuning and Training
Leverage compute capability 12.0 and about 77.6 TFLOPS of compute for custom training runs in PyTorch/CUDA without frequent out-of-memory errors.
High-Resolution Generative Media
Execute complex ComfyUI pipelines with multiple control nets and unquantized diffusion checkpoints loaded simultaneously in VRAM.
Heavy Workstation Rendering
Process detailed scene geometry and large texture caches backed by about 1222 GB/s of memory bandwidth.
Is it the right GPU for you?
Choose the RTX 6000D if your workloads require its substantial 84 GB VRAM capacity and Blackwell architecture features on a single workstation card. Opt for a smaller consumer or workstation GPU for lightweight inference to lower costs, or step up to a datacenter GPU if your workflow requires higher memory bandwidth.
Compare with similar GPUs
Frequently asked questions
Is the RTX 6000D suitable for LLM inference and fine-tuning?
Yes, its 84 GB of VRAM and about 1222 GB/s of memory bandwidth make it well-suited for hosting large weights and fine-tuning models. You can deploy inference servers immediately using our pre-configured vLLM and Ollama templates.
How does the RTX 6000D compare to other GPUs in memory and compute?
As a Blackwell workstation GPU with 84 GB of VRAM and compute capability 12.0, it offers more memory than standard consumer cards and earlier workstation generations. However, specialized datacenter GPUs may provide higher memory bandwidth than its about 1222 GB/s.
How do I connect to my RTX 6000D instance on ONIE?
You can connect directly via SSH access once your instance is running. We also provide ready templates for PyTorch/CUDA, ComfyUI, vLLM, and Ollama so you can start working right away.
How does billing work for this GPU?
Instances on ONIE use per-hour billing. You only pay for the time your RTX 6000D environment is active.
Rent the RTX 6000D by the hour
Create an account, choose a configuration and connect over SSH. Billing stops when you delete the GPU.
Rent RTX 6000D