Private AI in Your Virtual Private Cloud

Shepherd.

We make private AI in your VPC feasible.

RAM compression shrinks frontier models by 50–60%, cutting your hardware requirements in half, but keeping all the intelligence you need. Run a 31B parameter model on a single GPU instance, or on a Mac Studio with zero cloud dependency. Your data never leaves your infrastructure.

The real cost of private AI.

RAM compression doesn't just make models smaller. It makes an entirely different class of hardware viable, and that changes the economics of everything.

AWS

g7e.2xlarge

NVIDIA RTX PRO Server 6000, 96GB VRAM. RAM-compressed 31B model fits at 31GB with 65GB free for KV cache and batching.

On-Demand ~$8,700/yr*
Spot ~$2,700/yr*

*List pricing before corporate cloud discounts. 10hrs/day, workdays only.

Azure

NC24ads A100 v4

NVIDIA A100 80GB. Fits the compressed model with room to spare. Deploy in your Azure VNet with private endpoints.

On-Demand ~$9,500/yr*
Low-Priority ~$2,900/yr*

*List pricing before corporate cloud discounts. 10hrs/day, workdays only.

Google Cloud

a2-highgpu-1g

NVIDIA A100 40GB. The compressed 31B model fits within the 40GB envelope. Deploy in your GCP VPC with Private Service Connect.

On-Demand ~$9,500/yr*
Preemptible ~$2,900/yr*

*List pricing before corporate cloud discounts. 10hrs/day, workdays only.

Apple Silicon

Mac Studio

M4 Ultra with 192GB unified memory. Runs RAM-compressed models natively via MLX. On-prem, cloud-hosted, or at a desk.

One-time hardware ~$8,000
Running cost Electricity only

No cloud. No API keys. No metered costs. Runs 24/7.

What Shepherd deploys.

Shepherd is the platform that takes a frontier model, compresses it with RAM, validates it with Watchman, and deploys it to your infrastructure, whether that's a VPC, a Mac Studio fleet, or an air-gapped facility.

Available Now

Shepherd Enterprise Platform

  • Next-generation RAM compression engine, deployed in production now
  • CI/CD pipeline integration with automated compression on model release
  • Fleet deployment across Apple Silicon clusters and on-prem infrastructure
  • Air-gapped and sovereign deployment support
  • Batch compression workflows for model catalogues
  • Multi-format export: MLX, GGUF, and custom targets
  • Dedicated engineering support and SLA
Talk to Us About Enterprise
Powered by Watchman

Capability Assurance Built In

Every Shepherd Enterprise compression build includes an automated Watchman capability audit. You get a full quality report before any compressed model reaches production -- benchmark scores, capability drift analysis, and pass/fail gating against your quality thresholds.

No separate tooling. No manual validation. Compression and assurance in a single pipeline.

Next-Generation Compression

Our RAM compression engine produces smaller models with measurably higher quality than any publicly available technique. A ground-up rethink of quantization that changes what's possible at every compression level.

Enterprise-grade capabilities.

Production Pipeline Integration

Automated compression triggered on model release. Plug RAM into your existing CI/CD workflows with webhook triggers, CLI tooling, and API access. Compress once, deploy everywhere.

Broad Architecture Support

Dense, Mixture-of-Experts, multimodal. The RAM engine handles architectures that first-generation compression couldn't, with the same automated workflow and quality guarantees.

Fleet and Cluster Deployment

Deploy compressed models across Apple Silicon clusters, on-prem GPU infrastructure, or air-gapped environments. Sovereign deployment support for organisations that require it.

Quality-Gated Releases

Integrated Watchman audits gate every compressed build against your quality thresholds. Models that don't meet your standards never reach production. Full traceability from source to deployment.

Individual Edition.

The free individual edition of Shepherd is being rebuilt from the ground up with the same RAM compression engine powering the enterprise platform. When it ships, it will be a new generation -- not an incremental update.

Same Engine

The same next-generation compression technology available to enterprise customers, brought to your desktop.

Apple Silicon Native

Runs entirely locally on your Mac. No cloud, no sign-up, no data leaving your device.

Free When It Ships

The individual edition will remain 100% free for personal use. Same promise, dramatically better technology.

Notify Me When It Drops

Ready to compress at scale?

Talk to our team about deploying the Shepherd Enterprise platform in your infrastructure. Compression, capability assurance, and fleet deployment in a single pipeline.

Talk to Us

Looking for the free individual edition? Get notified when it ships.