Defines the minimum evidence that admits an artifact for parser and execution testing while explicitly withholding assistant-quality claims.
Implementation evidence: this topic is grounded in the reviewed GGUF.MiRust.com source snapshot. It documents observed code and artifacts without claiming broad deployment, model quality, or production readiness.
Architecture topic: this page does not claim that the WordPress website implements or executes the described runtime behavior.
Eligible sources
The runtime-smoke gate accepts deterministic-smoke and converted-trained source kinds only when the manifest validates against the exact artifact.
Required binding
Model byte count, SLM checksum, shape, tensor count, parameter count, quantization, source kind, admission status, quality claim, trained-quality claim, and next gate must match policy.
Meaning
Pass means the artifact is admitted for local runtime execution evidence. It does not mean useful language behavior, safety, broad browser support, license clearance, or production readiness.
Scope
This starter page defines the questions, boundaries, evidence, and failure modes that should be recorded before a capability is presented as supported.
Engineering considerations
- Identify the source, version, target environment, and owner.
- Separate observed values from estimates and externally reported values.
- Record trade-offs, unsupported cases, and fallback behavior.
- Link performance statements to a compatible benchmark methodology.
Verification questions
- What exact artifact, revision, backend, and environment were reviewed?
- Which assumptions could change the result?
- Which data should be retained so another engineer can reproduce the conclusion?