Portable Model Evidence
Embedding model bake-off
Public screening evidence selected static-retrieval-v1 for the full retrieval matrix.
Candidate results
| Profile | Status | nDCG@10 | Warm p95 | Peak RSS | Decision |
|---|---|---|---|---|---|
static-retrieval-v1 | selected-default | 0.5910 | 294.63 ms | 316.52 MiB | Best quality-cost Pareto point and promoted to the full public matrix. |
code-minilm-l12-v1 | resource-stop | 0.5273 | 1847.21 ms | 1.34 GiB | Stopped after one task because it exceeded both screening budgets and did not beat code MiniLM L6 quality. |
code-minilm-l6-v1 | rejected | 0.5330 | 1155.55 ms | 1.02 GiB | Crossed both laptop screening limits on its first completed task; the partial quality result is not an aggregate claim. |
general | rejected | 0.4466 | 1309.51 ms | 1.00 GiB | Crossed both laptop screening limits on its first completed task. |
Salesforce/SFR-Embedding-Code-400M_R | excluded | - | - | - | Non-commercial license and custom architecture are incompatible with the shipped default. |
jinaai/jina-code-embeddings-1.5b | excluded | - | - | - | The 1.5B-parameter custom model exceeds portable laptop download, memory, and inference budgets. |
nomic-ai/CodeRankEmbed | excluded | - | - | - | Custom NomicBERT architecture is not supported by the portable local inference backend. |
Claim boundary
The static profile is the only candidate that completed the screening matrix within the declared laptop budget. Resource-stopped rows are single-task observations, not aggregate quality claims.