SAVRN Cloud · Public preview
Build research workflows you can understand and govern
SAVRN Cloud brings model selection, research work and result review into one workspace on savrn.com. Two SAVRN-operated configurations are in preparation: Qwen3.5-9B Q6_K for utility work and Qwen3.8-27B Q5_K_M for coding tasks. Explore their intended roles and prepare a request in the public console. Connected execution is Coming soon; the preview returns clearly labeled browser-local samples.
Begin with the evidence you need
A useful research task specifies its sources, the question being asked and the form of an acceptable answer. SAVRN Cloud offers three guided starting points: Evidence review, Structured extraction and Research code. They help a team define that contract before evaluating a model. Use supplied public or invented material; a link in a prompt does not cause the preview to fetch a source.
Compare two prepared configurations
Qwen3.5-9B Q6_K is the utility candidate; Qwen3.8-27B Q5_K_M is the coding candidate. These are descriptions of specific prepared artifacts, not measured quality rankings or available commercial offers. Their proposed pilot limits are 8,192 total context tokens and 1,024 output tokens. Separate serving capacity, qualification and access approval remain pending.
Keep a request connected to its project
The console connects a prepared request to its selected project, intended candidate, demonstration fixture and sample usage receipt. A candidate profile supplies the intended model context; a fictional fixture supplies the browser demonstration. That distinction stays with the result so a reviewer can tell what was selected and what actually happened. Sample Work Credits illustrate recordkeeping, without publishing a customer price.
Build toward SAVRN-operated execution
The service direction is to run qualified model configurations on compute SAVRN operates, whether owned or specifically rented. A connected release needs an independently allocated serving lane, verified identity, task evaluations, measured performance, enforceable access and reconciled usage. Hardware changes and new quantizations require their own evidence.
Continue from a sample into a review
After exploring a starter, inspect its request receipt and identify what a real evaluation would need to establish. Projects, datasets, evaluation plans and Work Orders provide places to organize that next step. The public preview remains a browser-local workspace: it does not call a model, run supplied code, allocate GPUs or take payment.
Service maturity
Explore the workflow today
Compare two prepared SAVRN model candidates and explore three guided starters through labeled browser-local samples.
Before connected service access
Connected execution requires independently allocated SAVRN-operated capacity, completed qualification, approved access and validated accounting.
What this makes possible
The intended outcome is a research workflow whose scope, execution choices and review evidence remain understandable as teams and infrastructure change.
Explore the SAVRN Cloud platform
Compare prepared models for the work you need to do
Compare SAVRN Cloud’s prepared Qwen3.5-9B Q6_K and Qwen3.8-27B Q5_K_M configurations, proposed limits and qualification status. Connected execution is Coming soon.
Run · Inference playgroundPrepare a useful request, then inspect the sample record
Prepare evidence review, structured extraction or research-code requests in SAVRN Cloud. Inspect intended Qwen candidates and clearly labeled browser sample receipts.
Govern · ProjectsGive research activity a clear project context
Explore project organization, sample budgets and linked research activity in SAVRN Cloud. Hosted project access and enforced team permissions are coming soon.
Run · ComputeMatch execution choices to the work you need to run
Explore workload placement and compute configuration in SAVRN Cloud’s simulated console. Connected rented and owned infrastructure options are coming soon.
Run · DeploymentsUnderstand a deployment from creation to retirement
Explore deployment configuration, request draining, restart and deletion in SAVRN Cloud’s public preview. Connected deployment control is coming soon.
Run · SandboxesMake a task’s execution boundary explicit
Explore bounded task execution, sample limits and exported results in SAVRN Cloud. The preview runs built-in browser tasks; connected sandboxes are coming soon.
Improve · EvaluationsEvaluate the behavior your research task requires
Explore task-specific baselines, case results and evaluation receipts in SAVRN Cloud. Public preview scores are synthetic; connected evaluations are coming soon.
Improve · EnvironmentsTurn task expectations into a reviewable definition
Explore task definitions, versioned rubrics and pass criteria in SAVRN Cloud’s public preview. Connected evaluation and training environments are coming soon.
Improve · DatasetsKnow which data a research workflow is allowed to use
Discover datasets in SAVRN’s existing catalog and explore planned Cloud workflows for provenance, rights, evaluation splits and controlled dataset revisions.
Improve · TrainingTreat model adaptation as a controlled experiment
Explore adapter recipes, dataset purpose and candidate handoff in SAVRN Cloud. Training runs are simulated; connected model adaptation is coming soon.
Improve · CandidatesKeep a promising candidate separate from an active release
Explore candidate evaluation, reviewer approval, promotion and rollback in SAVRN Cloud. All releases in the public preview are browser-local simulations.
Govern · Work OrdersDefine the work and the result you expect
Explore scoped research Work Orders, approval, sample execution and deliverable acceptance in SAVRN Cloud. Connected research workflows are coming soon.
Govern · ApprovalsMake authorization a specific, recorded decision
Explore how SAVRN Cloud separates approval authority, task scope and budget decisions from execution and deliverable acceptance. Connected approvals are coming soon.
Govern · UsageConnect resource use to the work that produced it
Explore project usage, reservations and sample Work Credit receipts in SAVRN Cloud. The public preview illustrates accounting without charges or payments.
Develop · API keysScope access to the actions an application needs
Explore the planned lifecycle of scoped project credentials in SAVRN Cloud. Preview keys are simulated values; live API access and SDKs are coming soon.
Operate · CapacitySeparate resource inventory from usable capacity
Explore how SAVRN Cloud distinguishes resource inventory, workload qualification and available capacity. All provider and owned-resource records are simulated.
Operate · OperationsTurn operational events into understandable actions
Explore readiness checks, incident states and operational evidence in SAVRN Cloud’s public preview. Connected monitoring and service operations are coming soon.
Understand · ArchitectureKeep the research workflow portable as compute changes
Explore SAVRN Cloud’s planned separation of research workflows, governance and execution, including a qualified path from rented capacity to owned infrastructure.
Understand · RoadmapUnderstand what must be ready before a service launches
Review SAVRN Cloud’s planned service progression and the distinction between a public preview, qualified capability and a connected customer release.
Govern · Workspace settingsUnderstand which settings are preferences and which need enforcement
Explore workspace preferences, session export and reset in SAVRN Cloud. Preview retention and placement choices are local settings, not enforced service policies.
Build toward the work that matters.
Tell SAVRN what your institution needs to run, who reviews the results and where its data must stay. That workload defines the next service to qualify.
Discuss an AI project