Architecture001 DEV generation — peak dedicated GPU
Architecture001 DEV generation — peak dedicated GPU: 9.81 GiB on a 12 GB card.
Single reading
10,529,382,400 bytes
Protocol
Test definition
GPU memory telemetry from the project's watcher / allocator counters. Watcher telemetry, 43 samples; allocator peak 10,332,667,904 under the 10,468,982,784 cap.
Limits
Limitations
- Sampled gauges; sub-sample transients not exhaustively proven. Physical card is 12,227 MiB; allocator and dedicated readings are different counters.
Log
Recorded values
| Date | Value | Evidence | Samples | Source |
|---|---|---|---|---|
| 21 September 2026 | 10,529,382,400 bytes | MEASURED | — | docs/ledger/FINAL_LM_MODEL_LIMITATION_AND_NEXT_ARCHITECTURE_DECISION.md |
Source paths refer to the private JARVIS repository and runtime records. They are listed for audit and are not published.