Loading the SOTA2 catalog…
Cactus
One inference engine for on-device AI across smartphones, laptops, and edge hardware.
What is Cactus?
One inference engine for on-device AI across smartphones, laptops, and edge hardware. Runs LLMs, transcription, and embeddings locally with automatic cloud fallback. Also referred to as Cactus Hybrid Cloud and Cactus Engine.
Product typeEdge AI
Pricing ·
DeploymentSelf-hosted
APINot available
What teams use Cactus for
On-device LLM inference
Local transcription
Local embeddings
Hybrid cloud routing for AI inference
Mobile voice assistant
Desktop notetaker
Wearable intelligence for smart glasses and AR devices
Integrations and access
Platforms, integrations, and language support vary by plan and region. Confirm final requirements with the vendor.
Platforms
IntegrationsAPI and webhooks
Languages
Support
What reviewers say
Community reviewsReviews are owned and editable by their authors.
Sign in to reviewLoading community reviews…
Enterprise readiness
Compliance claims are normalized from current vendor documentation and independently reviewed by SOTA2.
Zero-copy memory mapping
Zero network transmission during on-device inference
Open-source MIT-licensed auditable codebase
Configurable cloud routing with disablement option
Data retention:
Benchmarks and comparisons
Independent benchmarksStructured task results are being verified.
Side-by-side comparisonsComparison workspaces will be available in a later release.
