Retrace-1.5BvsWhisper-Lite
Decision Card metrics — latency, license, lineage overlap, benchmarks, and repo health from the live graph.
Model ARetrace
Retrace-1.5B
1graph score
Open model page →Model BWhisperWhisper-Lite
0graph score
Open model page →Retrace-1.5B leads on graph popularity (1 vs 0)
Decision metrics
| Attribute | Retrace-1.5B | Whisper-Lite |
|---|---|---|
| License | — | — |
| ParametersModel size | — | — |
| Context window | — | — |
| Architecture | — | — |
| Hardware class | — | — |
| Latency | — | — |
| $ / 1M tokens | — | — |
| Verified TTFT | — | — |
| Repo health (RIS) | 24 | — |
| Graph trust | 88 | 88 |
| Lineage | 10 papers · 1 repo | 8 papers |
| Graph score | 1 | 0 |
Decision cards
Retrace-1.5B
License—
Parameters—
Context—
Architecture—
Lifecycle
Lineage
BenchmarksPending verified runs
Repo health
RIS 24estimated
retrace-agents →Economics—Economics pending verified runs
Whisper-Lite
License—
Parameters—
Context—
Architecture—
Lifecycle
Lineage
BenchmarksPending verified runs
Repo healthNo linked repo
Economics—Economics pending verified runs
Retrace-1.5B
A small reasoning model tuned to self-correct via failure traces.