Read-only preview
Compute, Thermals and Power
GPU / Local AI
Quadro and RTX behaviour, VRAM limits, and running local models on workstation hardware.
2 threads · 3 posts
| Thread | Started by | Replies | Views | Last post |
|---|---|---|---|---|
| Pinned VRAM is the binding constraint for local models, not compute | fury_g11_daily | 1 | 2411 | |
| Running a local model on battery: expectations | median_of_five | 0 | 733 |