GPU Cloud
RTX Pro 6000 GPU cloud for open-model inference
Rent NVIDIA RTX Pro 6000 Blackwell GPUs with 96 GB of VRAM. Run hourly GPU workspaces, reserve dedicated inference endpoints, or call open models through an OpenAI-compatible API — for Qwen, Gemma, image, RAG, fine-tuning, and coding workloads.
At a glance
RTX Pro 6000 Server Edition
- GPU
- RTX Pro 6000 (Blackwell)
- VRAM
- 96 GB
- Configurations
- 1 / 2 / 4 / 8 GPUs
- On-demand
- $1.89 / GPU-hour
Current on-demand rate: $1.89/GPU-hour, billed per second. See pricing for the live rate.
What it's good for
Workloads that fit 96 GB
RTX Pro 6000 is EcoHash's hero GPU for cost-effective open-model inference and GPU workspaces.
20B–35B open models
96 GB of VRAM fits popular 20B–35B models with room for larger batch sizes and KV-cache headroom.
LoRA & QLoRA fine-tuning
Adapter fine-tuning and experimentation on a single Blackwell GPU, with root access and a browser terminal.
Quantized larger models
Validate selected quantized larger models where 96 GB is enough for single-GPU inference.
Batch & data jobs
Batch inference, data preprocessing, and offline evaluation on workstation-class GPUs.
Best-fit models
Popular models on RTX Pro 6000
Start with these open models through the API, then move to a dedicated endpoint or GPU workspace as usage grows.
Voice and lightweight models (such as Kokoro TTS and Whisper STT) are available through the same API and can scale onto EcoHash GPU capacity for high-throughput workloads — they don't require a dedicated RTX Pro 6000.
Product options
Three ways to use it
GPU workspace
Launch an hourly RTX Pro 6000 instance with root access, Jupyter, and a web terminal.
Best for tuning, rendering, and experimentation.
Dedicated endpoint
Reserve RTX Pro 6000 capacity for predictable latency and throughput on your chosen model.
Best for steady production traffic.
Hosted model API
Call open models through one OpenAI-compatible API — no GPU to manage until you need one.
Best for getting started fast.
GPU workspace
From a single GPU to a cluster
Provision exactly what a job needs and tear it down when you're done — root access, a browser terminal, and per-GPU-hour billing.
Hourly GPU instances
Launch single-GPU or multi-GPU pods with SSH, Jupyter, and a browser terminal.
Multi-replica clusters
Scale to multiple replicas for distributed training or multi-node serving, managed from one panel.
Web terminal
Drop into a shell from any browser — no SSH key required.
File upload
Upload files straight into your pod from the console.
Auto-expiry protection
Set a duration and instances stop automatically, so you never get a surprise bill.
3D rendering & ray tracing
Render in Blender, Octane and more on Blackwell RT cores with 96 GB — workstation-class GPUs that clouds renting H100/A100 don't offer.
Storage
Persistent storage that travels with your work
Keep datasets and model weights close to the GPUs. Storage outlives any single instance and reattaches on demand.
Cloud Drive
Block storage (read-write-once) for a single instance — a durable workspace that survives restarts.
Shared Filesystem
CephFS-backed shared storage (read-write-many) mounted across replicas — ideal for datasets and model weights.
Seamless mounts
Attach storage to any GPU instance; your first drive mounts automatically.
5-day grace period
Suspended storage stays readable for five days, so you can download your data before it is removed.
Boundaries
What it's not for
RTX Pro 6000 is best for 20B–35B open models, selected quantized larger models, and production inference workloads. Very large models (235B+ / 671B) that need multi-GPU tensor sharding are better served by H200 or a partner path. RTX Pro 6000 is offered as PCIe capacity for single-GPU and multi-instance inference, not as an NVLink training cluster.