[ LAB — LIVE · no model calls ]
Local Memory Planner
Estimate raw weight storage from parameter count and precision, add an explicit planning allowance and compare it with available memory. See both decimal GB and binary GiB. The tool deliberately avoids promising that a model fits or will run quickly.
All lab toolsInteractive workbench / no model calls
How to use it
- 01
Enter total checkpoint parameters, not only active parameters for an MoE model.
- 02
Choose nominal bits per weight and a separate percentage allowance for planning.
- 03
Compare with available memory and measure the real runtime under your target context and concurrency.