A new open-source UEFI tool boots from USB and unlocks significant extra tensor performance on RTX 20, 30, and 40-series desktop and laptop GPUs, making the half-speed AI throttle hack a whole lot easier to try on Windows. No VBIOS flash or patched driver needed: the tool runs from a FAT32 stick before the Nvidia driver loads at every boot, and then voila, the developer’s own laptop RTX 4060 hit 65% higher FP16 math.
The “UEFI pre-driver NVIDIA GPU unlocker,” or nv-uefi-unlocker project, removes Nvidia’s tensor limiter using the community V67 payload with read-back verification. This tricks Nvidia’s signed Booter firmware into opening the write lock on two speed-selector registers, allowing the tensor units to run at full rate. The unlock can now run entirely from a bootable USB drive, on Windows as well as Linux, whereas previously it worked primarily through manually installed Linux modules, with Windows support only experimental. The read-back verification part makes things safer, which was a concern with the experimental builds.
The release ships only scripts and self-built binaries, without any Nvidia firmware in the download. 03 driver packages, verifies them, then rebuilds the firmware files locally. The project credits Zagitta’s gpu-unlock as its porting source and builds on several other community projects, including the RTX 40 fork gpu-unlock-ada and an earlier Windows EFI tool. Having one tool for the many GeForce owners on Windows should significantly open up the hack to a wider audience. Previously, it was scarier-looking, and project progression is rapid these days with AI tools .
Source link







