Local AI workstation for private inference with up to 192 GB of unified memory and 32 GB Radeon GPU
Cloud infrastructure for your code and agents
Stage
Not given
Startup
Founded
Not given
2024
Based in
Not given
US
Pricing model
Paid
Freemium
Pricing
Developer: starting at $5,999 USD (128 GB memory, 2 TB storage). Memory upgrade to 192 GB adds $2,200. Storage upgrade to 4 TB adds $250. Cluster kit $799 per machine. Business pricing available by quote. Worldwide shipping, import duties and taxes outside US included. No sales tax in US.
Starter: Free with $100 in credits; Team: $200/mo (annual) or $250/mo (monthly) with $100/mo credits. Usage-based rates: Code Reviews $1.00 per review, x64 Runners $0.002 per vCPU/minute, macOS Runners $0.020 per vCPU/minute, Sandbox vCPU $0.000014 per second, Sandbox Memory $0.0000045 per GiB/secon
Key features
Run DeepSeek V4 Flash and Qwen 27B models
Browser-based setup over encrypted Bluetooth
Private OpenAI-compatible API
Lucebox Mix: run two models simultaneously
Headless Ubuntu Server with pre-installed inference engine
Optional Tailscale integration for remote access
Optional cluster kit with 100 GbE networking
Instant sandboxes that boot in under one second
GitHub Actions runners for x64 and macOS
AI-powered code review on every pull request
Support for Go, TypeScript, and Python SDKs
Git operations including clone, checkout, and diff
Persistent volumes and snapshots
Outbound domain and CIDR allowlists
Pre-built container images
OpenCode integration for AI workflows
Configurable CPU and memory options
What makes it different
No per-token billing or cloud dependencies
1.5x faster decode speed than DGX Spark
Hardware and software co-designed for optimal performance
Completely private: runs offline with no cloud proxy
Open source inference engine with tuned models
Bare-metal infrastructure for 30% faster performance and up to 60% cheaper than alternatives
Sandboxes boot in under one second, enabling instant isolation for AI agents
AI code review that reads your full codebase and reviews every PR
Drop-in GitHub Actions replacement requiring no configuration changes
Infrastructure built specifically for AI agents to write, run, and ship code
Lucebox
Tenki