AI Deployment Catalog
Pre-configured templates for every AI workload. Pick a template, deploy in minutes, and start building.
Type
Your tier
Llama 3.3 8B
Local LLM Deployments
Fast, lightweight model for chatbots, agents, and rapid prototyping.
Qwen 2.5 32B
Local LLM Deployments
Powerful multilingual model with strong coding and reasoning.
Llama 3.3 70B
Local LLM Deployments
Top-tier open model for complex reasoning and production workloads.
Mistral Large 2
Local LLM Deployments
Flagship Mistral model — multilingual, code, and reasoning.
Qwen 2.5 72B (FP16)
Local LLM Deployments
Best-in-class multilingual and reasoning at full precision.
DeepSeek V3
Local LLM Deployments
Frontier-scale reasoning and code generation — quantized for 128 GB.
Llama 3.1 405B (Q4)
Local LLM Deployments
Largest open model — quantized to fit 128 GB unified memory.
OpenClaw Agent
Agent Hosting
OpenClaw with a connected local Llama backend. Autonomous AI agent running 24/7.
AutoGPT
Agent Hosting
AutoGPT with Ollama backend — self-prompting AI agent.
CrewAI Workspace
Agent Hosting
CrewAI workspace with Jupyter and pre-installed dependencies.
LangGraph Studio
Agent Hosting
LangGraph Studio for building and debugging agent workflows.
MLX + Jupyter Lab
AI Development Environment
Apple MLX framework with Jupyter Lab, Python 3.12, and the full ML stack.
Core ML Environment
AI Development Environment
Core ML conversion environment with Xcode CLI tools.
VSCode Server
AI Development Environment
VSCode web-IDE with ML extensions, pre-configured for AI development.
LiteLLM Multi-Model
Multi-Model Orchestration
One endpoint, many models. Route requests across Llama, Qwen, Mistral with a unified API.
Blank Apple Silicon
Custom Deployments
Fresh macOS with SSH and browser VNC. Install anything you want.
Showing 16 of 16 templates