Direct answer
Storage, load success, representative-task peak, sustained peak, and device support are different claims and require different evidence.
This page does not publish benchmark or compatibility results. It shows the evidence required to answer multimodal AI memory planning without turning an assumption into a product claim.
Evidence to collect
The claim becomes reviewable only when the following evidence is attached to the same artifact and test run:
- Source and working dimensions
- Tensor lifetime
- Repeated capture or audio sequence
A device badge must come from an exact device, OS, artifact, runtime, backend, and workload record, not parameter-count intuition.
Implementation workflow
- Record the exact artifact and format.
- Measure the app before model load.
- Measure after model initialization.
- Run a representative product task.
- Repeat the fixed workload without restarting.
- Store failures, fallback, and cleanup behavior.
Keep each transition observable. A failure should identify the stage, artifact, runtime, and recovery action without logging private user content.
Failure patterns to prevent
- Text-only validation
- Keeping duplicate bitmaps
Also prevent silent fallback, unpinned artifacts, missing cancellation, and conclusions that combine unlike configurations. Store unsuccessful runs alongside successful ones.
Minimum reproducibility record
| Layer | Record |
|---|---|
| Device | Manufacturer, model, chipset, RAM class, operating-system build |
| Software | Application version and git commit |
| Model | Family, variant, revision, format, file length, hash, quantization |
| Runtime | Name, revision, requested backend, observed backend evidence |
| Workload | Fixture revision, input hash, prompt hash, output policy |
| Outcome | Completed, failed, cancelled, fallback, and privacy-safe diagnostics |
Release checklist
- ☐ The primary query is answered without an unsupported number.
- ☐ Every artifact and runtime is pinned.
- ☐ The representative task and failure policy are explicit.
- ☐ Lifecycle, cancellation, cleanup, and fallback are tested.
- ☐ User-content and network boundaries are documented.
- ☐ Result wording applies only to the recorded configuration.
- ☐ The page links to raw method or evidence when results are added.
Sources and related evidence
This page relies on the Cove fact ledger and benchmark policy. Results remain blocked until raw records exist.
Chinese deployment and troubleshooting content is organized in the 奇连 AI 端侧专题.