diff --git a/README.md b/README.md
index e07c19a8a0215df80735a7d535e2e3032c76a12a..d05c2c28688d6653d15cac841df0b641e504a958 100644
--- a/README.md
+++ b/README.md
@@ -19,11 +19,11 @@ For business inquiries, please visit our website and submit the form: [NVIDIA Re
 ## Requirements
 
 - Both Windows and Linux are supported.
-- [CUDA](https://developer.nvidia.com/cuda-toolkit) __v10.2 or higher__, a __C++14__ capable compiler, and [CMake](https://cmake.org/) __v3.19 or higher__.
-- A high-end NVIDIA GPU that supports TensorCores and has a large amount of memory. The framework was tested primarily with an RTX 3090.
-- __(optional)__ [Python](https://www.python.org/) __3.7 or higher__ for interactive bindings. Also, run `pip install -r requirements.txt`.
+- __NVIDIA GPU__ with __compute capability 75 or higher (RTX 20XX or newer)__. All shown results come from an RTX 3090.
+- __[CUDA](https://developer.nvidia.com/cuda-toolkit) v10.2 or higher__, a __C++14__ capable compiler, and __[CMake](https://cmake.org/) v3.19 or higher__.
+- __(optional) [Python](https://www.python.org/) 3.7 or higher__ for interactive bindings. Also, run `pip install -r requirements.txt`.
   - On some machines, `pyexr` refuses to install via `pip`. This can be resolved by installing OpenEXR from [here](https://www.lfd.uci.edu/~gohlke/pythonlibs/#openexr).
-- __(optional)__ [OptiX](https://developer.nvidia.com/optix) __7.3 or higher__ for faster mesh SDF training. Set the environment variable `OptiX_INSTALL_DIR` to the installation directory if it is not discovered automatically.
+- __(optional) [OptiX](https://developer.nvidia.com/optix) 7.3 or higher__ for faster mesh SDF training. Set the environment variable `OptiX_INSTALL_DIR` to the installation directory if it is not discovered automatically.
 
 
 If you are using Linux, install the following packages