nvidia-turing

Pre-driver FMLA32 Tensor Core unlocker and PTX benchmark console for GeForce RTX 40-series, RTX 30-series and RTX 20-series on Windows 10/11 (UEFI USB) and Linux (gpu_unlock.ko), with friendly UI for Win/Linux. Restores full 2x FP16/BF16/TF32->FP32 accumulate rate with automatic hardware profiling, pre-flight ROM checks, and zero VBIOS flashing.

Unofficial FreeToken fork: Flash-Next 125B at 38 tok/s on two RTX 3060s with 2-bit experts, gpt-oss-120b on one; a benchmark tunes your settings. Qwen3.8-Flash-Next, 12 GB, MTP, 250k context, image input, WSL2. Runs on Turing: RTX 2060, RTX 20 series, sm_75.

Rust CLI that makes NVIDIA Turing GPUs work on macOS 15 Sequoia via OpenCore + the NullMoth driver — automatic OpenCore config repair, verified always-latest driver install, and OpenCore EFI generation. Validated on real hardware: GTX 1650 Mobile, 1440p@144Hz HDMI, Metal 3.

Fix for external HDMI monitors not waking after suspend on NVIDIA GPUs on Fedora 44 with GNOME Wayland. Works with nouveau and with the NVIDIA proprietary module (GSP disabled).

Reproducible FreeToken MoE expert-offload compatibility lab and benchmarks for NVIDIA Turing sm_75.