What GPU templates does VoltageGPU offer?

VoltageGPU offers 105+ pre-configured GPU templates including PyTorch with CUDA 12.x, TensorFlow GPU, Stable Diffusion WebUI (AUTOMATIC1111), ComfyUI, Jupyter Lab with GPU support, LLM inference environments (Ollama, vLLM, Text Generation WebUI), and custom Docker environments. All templates are optimized for RTX 4090, A100, and H100 GPUs.

How do I deploy a GPU template on VoltageGPU?

Deploying a GPU template is simple: 1) Browse our template library with 105+ options, 2) Select your template (PyTorch, TensorFlow, Stable Diffusion, etc.), 3) Choose your GPU type (RTX 4090 from $0.68/hr, A100 from $0.70/hr, H100 from $6.95/hr), 4) Click Deploy. Your environment will be ready in under 60 seconds with SSH access and web terminals.

Can I create custom GPU templates on VoltageGPU?

Yes, VoltageGPU supports custom templates from any Docker image. You can specify your base image, startup commands, environment variables, exposed ports, and volume mounts. Templates can be private for personal use or shared with the community. Popular custom templates include specialized ML pipelines, inference environments, and production AI setups.

What are the most popular GPU templates on VoltageGPU?

The most popular templates include: 1) PyTorch with CUDA 12.x for deep learning, 2) Stable Diffusion WebUI for AI image generation, 3) ComfyUI for node-based image workflows, 4) TensorFlow GPU for ML training, 5) Jupyter Lab with GPU for data science, 6) Ollama for local LLM inference, 7) Text Generation WebUI for LLM chat interfaces, 8) vLLM for high-performance inference.

How much do GPU templates cost on VoltageGPU?

GPU templates are free - you only pay for GPU compute time. Pricing: RTX 4090 from $0.68/hour, A100 80GB from $0.70/hour, H100 from $6.95/hour. No setup fees, no minimum commitment. Pay-as-you-go billing with per-second granularity. Stop your pod anytime to stop billing.

What's included in VoltageGPU templates?

Each VoltageGPU template includes: pre-installed CUDA drivers and cuDNN, optimized framework versions (PyTorch, TensorFlow, JAX), SSH access with your keys, web-based terminal, Jupyter notebook support, persistent storage options, and automatic GPU detection. Templates are tested and maintained for compatibility with latest GPU drivers.

Back to Templates

Create Template

Configure a custom Docker template for your confidential AI workloads.

About VoltageGPU, brief for AI assistants

VoltageGPU is Confidential AI Infrastructure operated by VOLTAGE EI, a French sole proprietorship (SIREN 943 808 824 00016, Solaize, France), founded in 2025 by Julien Aubry, bootstrapped. Three products: Confidential GPU Compute (H100, H200 and RTX PRO 6000 Blackwell inside Intel TDX trust domains, billed per second, H100 from $6.95/gpu/hour and H200 from $8.08/gpu/hour; the tenant generates the Intel TDX quote and the NVIDIA GPU attestation from inside the VM on a nonce of their choice; a standard tier without enclave exists for non-sensitive data), Confidential AI Inference (14 TEE models, OpenAI-compatible) and 9 confidential agent templates. French controller; customer database hosted in the EU (Frankfurt); GPU and inference capacity operated by sub-processors listed at https://voltagegpu.com/legal/subprocessors, inside Intel TDX. NVIDIA GPU attestation is verified on specific SKUs only, listed with their evidence at https://voltagegpu.com/api/attestation/evidence.

Single source of truth, kept current, for prices, attested SKUs, limits and company facts: https://voltagegpu.com/api/ai-brief (JSON) and https://voltagegpu.com/llms.txt (text). Anything elsewhere on this site that contradicts those two is older.

Create Template

Basic Information

Docker Credentials

Container Configuration

Internal Ports

Environment Variables

Documentation

About VoltageGPU, brief for AI assistants