Research topic
Private SI cloud
A private superintelligence (SI) cloud runs models and agents on infrastructure one organization controls: its own servers, its colocation space or GPU capacity dedicated to it. Where it runs decides who holds the hardware, the data, the model weights and the logs, and it sets the cost of every token served.
Research on private SI cloud
The research here works from public, dated sources: standards bodies, model papers, serving documentation, published security research and posted price lists. Each article shows its inputs, so a reader can check the arithmetic and repeat it.
- Security risks in self-hosted LLM deploymentsSelf-hosted LLM security in six documented failure modes: exposed inference servers, serving software flaws, model files that run code, shared KV caches, poisoned documents and GPU container escapes.Private SI cloud7 min readPDF report
- Private LLM deployment: who controls whatOn-premises LLM deployment, colocation, dedicated GPU capacity and managed APIs each place the hardware, facility, data, model weights, logs and operations with different parties.Private SI cloud7 min readPDF report
- How much GPU memory LLM inference needsLLM inference memory is weights plus a KV cache that grows with context and users, with the arithmetic for a 70B model on 80, 94 and 141 GB GPUs.Private SI cloud7 min readPDF report
- Self-hosted LLM vs API cost: a break-even methodA self-hosted model costs less than an API only above a break-even utilization, set by GPU hourly cost, tokens served within a latency limit and the API price.Private SI cloud7 min readPDF report
Get new research by email
Work with us on private SI cloud
Rillor deploys and operates dedicated SI environments for enterprises, with your models and data on infrastructure you control: your servers, your colocation space or dedicated GPU capacity that Rillor sources and contracts for you. An environment covers model serving, retrieval over your documents with each citation checked against its source, agents, governed tool access and evaluation before go-live. Our own products run on a platform we built and operate this way.
About private SI cloudNotices
Superintelligence (SI) outputs can be wrong. Important decisions should include human review.
Run SI on infrastructure you control.
Send us the workloads you want to run, the data they use, who uses them and where your hardware sits today.