AI Platform
GPU Templates
Deploy production-ready AI stacks in 60 seconds. Optimized for performance and ease of use.
One-click Ubuntu PyTorch
Pre-configured Ubuntu environment with latest PyTorch, CUDA, and cuDNN. Ready for training.
Image: ispeedhost/ubuntu-pytorch:cuda12.1
- Ubuntu 22.04 LTS
- PyTorch 2.0+
One-click JupyterLab
Instant browser-based notebook environment. Secure, persistent, and powerful.
Image: ispeedhost/jupyterlab-pytorch:cuda12.1
- Browser access
- Pre-installed libs
vLLM Inference
Production inference template for high-throughput LLM serving. Optimized for RTX and A100/H100.
Image: ispeedhost/vllm:latest
- OpenAI API compatible
- PagedAttention support
Whisper (Speech-to-Text)
Speech-to-text API for high-quality transcription. GPU accelerated for fast processing.
Image: ispeedhost/whisper:latest
- Speech-to-text API
- GPU accelerated
Ollama
Run LLMs easily with a simple API. Great for experiments and development.
Image: ispeedhost/ollama:latest
- Run LLMs easily
- Great for experiments + dev
ComfyUI
Node-based image workflows with a web-based interface. Web UI included and ready to go.
Image: ispeedhost/comfyui:latest
- Node-based image workflows
- Web UI included
AI Toolkit
General AI utilities container for various tasks. Great for batch jobs and automation.
Image: ispeedhost/aitoolkit:latest
- General AI utilities container
- Great for batch jobs
Global GPU Availability
We offer a wide range of NVIDIA GPUs across multiple regions. Check the console for real-time availability and pricing in your preferred location.
Ready to scale your infrastructure? Start your journey with iSpeedHost today.
Deploy your first instance in minutes. No credit card required to explore the console.
Get Started Now