Run AI agents and inference pipelines on sovereign, region-selected compute.
AI labs, SaaS platforms, and enterprise teams run AI agents, RAG pipelines, and vector databases on ZCP today, on CPU and high-RAM VM instances. GPU-accelerated instances for large model training and inference are on the roadmap.
GPU instances, coming soon
CPU and high-RAM VM instances are available today for AI agents, RAG pipelines, embeddings, and CPU-optimized inference. GPU-accelerated compute for large model training and high-throughput inference is on the roadmap. Join the waitlist.
CPU and high-RAM VMs, available now
High-memory instances (up to 96 GB RAM, 48 vCPU) run AI agent frameworks, embedding pipelines, small-model inference, and RAG orchestration today. No GPU required for most agent workloads.
Your jurisdiction, your control
Training data and model weights stay in the region you select, under a single named operator. Useful when export-control regimes, customer contracts, or internal policy restrict where sensitive AI development runs.
Vector DB and RAG infrastructure
Persistent NVMe block storage and high-RAM VMs run Weaviate, Qdrant, Chroma, or pgvector at scale. S3-compatible object storage for training data and model checkpoints.
GPU instances, coming soon
GPU-accelerated compute for large model training, fine-tuning, and high-throughput inference is on the roadmap. Join the waitlist and we will notify you when GPU instances are available.
Common workloads
What organizations in this space typically run on ZCP.
AI agent hosting
Deploy multi-agent frameworks, LangChain, AutoGen, CrewAI, LlamaIndex, on high-RAM VM instances (up to 96 GB). Run agent orchestration, tool-calling loops, and memory systems on dedicated CPU compute. Available now.
RAG pipeline infrastructure
Vector databases, document chunking, embedding pipelines, and retrieval APIs on dedicated, region-controlled compute. No shared-tenant resource contention. NVMe block storage for index persistence.
LLM inference, CPU-optimized
Run llama.cpp, Ollama, or vLLM with CPU-optimized models (Phi-3, Mistral 7B quantized, Gemma 2B) on high-core-count VM instances. Practical for agent sub-tasks, classification, and summarization at lower cost.
Embedding generation
Bulk embedding jobs on large-vCPU instances for indexing pipelines, semantic search, and document retrieval. Predictable CAD compute cost, no per-token billing, no shared quota limits.
MLOps and experiment tracking
Host MLflow, DVC, or custom experiment tracking on dedicated VMs with persistent NVMe storage. Keep training runs, metrics, and model artifacts under your control.
GPU training and large-model inference
Coming soonFull GPU instance support for large model training, LoRA fine-tuning, and high-throughput inference serving. Not yet available; coming soon. Join the waitlist.
Get started
Start building on
sovereign cloud today.
New accounts get $300 in credit, valid for 60 days. No commitment. Or talk to our team about a private cloud build-out.
Offer ends Jul 14, 2026 · New accounts only · Terms apply · ZSoftly Technologies Inc., Ottawa ON