diff --git a/docs/docs/features/ml-hardware-acceleration.md b/docs/docs/features/ml-hardware-acceleration.md
index a7229f1b9a..b45884b0f0 100644
--- a/docs/docs/features/ml-hardware-acceleration.md
+++ b/docs/docs/features/ml-hardware-acceleration.md
@@ -20,6 +20,7 @@ You do not need to redo any machine learning jobs after enabling hardware accele
 - Only Linux and Windows (through WSL2) servers are supported.
 - ARM NN is only supported on devices with Mali GPUs. Other Arm devices are not supported.
 - Some models may not be compatible with certain backends. CUDA is the most reliable.
+- Search latency isn't improved by ARM NN due to model compatibility issues preventing its use. However, smart search jobs do make use of ARM NN.
 
 ## Prerequisites
 
@@ -34,6 +35,7 @@ You do not need to redo any machine learning jobs after enabling hardware accele
   - The `hwaccel.ml.yml` file assumes the path to it is `/usr/lib/libmali.so`, so update accordingly if it is elsewhere
   - The `hwaccel.ml.yml` file assumes an additional file `/lib/firmware/mali_csffw.bin`, so update accordingly if your device's driver does not require this file
 - Optional: Configure your `.env` file, see [environment variables](/docs/install/environment-variables) for ARM NN specific settings
+  - In particular, the `MACHINE_LEARNING_ANN_FP16_TURBO` can significantly improve performance at the cost of very slightly lower accuracy
 
 #### CUDA
 
@@ -50,12 +52,13 @@ You do not need to redo any machine learning jobs after enabling hardware accele
 
 #### RKNN
 
-- You must have a supported Rockchip SoC, only RK3566 and RK3588 are supported at this moment.
+- You must have a supported Rockchip SoC: only RK3566, RK3576 and RK3588 are supported at this moment.
 - Make sure you have the appropriate linux kernel driver installed
   - This is usually pre-installed on the device vendor's Linux images
 - RKNPU driver V0.9.8 or later must be available in the host server
   - You may confirm this by running `cat /sys/kernel/debug/rknpu/version` to check the version
 - Optional: Configure your `.env` file, see [environment variables](/docs/install/environment-variables) for RKNN specific settings
+  - In particular, setting `MACHINE_LEARNING_RKNN_THREADS` to 2 or 3 can *dramatically* improve performance for RK3576 and RK3588 compared to the default of 1, at the expense of multiplying the amount of RAM each model uses by that amount.
 
 ## Setup
 
@@ -137,3 +140,12 @@ Note that you should increase job concurrencies to increase overall utilization
 - If you encounter an error when a model is running, try a different model to see if the issue is model-specific.
 - You may want to increase concurrency past the default for higher utilization. However, keep in mind that this will also increase VRAM consumption.
 - Larger models benefit more from hardware acceleration, if you have the VRAM for them.
+- Compared to ARM NN, RKNPU has:
+  - Wider model support (including for search, which ARM NN does not accelerate)
+  - Less heat generation
+  - Very slightly lower accuracy (RKNPU always uses FP16, while ARM NN by default uses higher precision FP32 unless `MACHINE_LEARNING_ANN_FP16_TURBO` is enabled)
+  - Varying speed:
+    - If `MACHINE_LEARNING_RKNN_THREADS` is at the default of 1, RKNPU will be substantially slower than ARM NN in most cases
+    - If `MACHINE_LEARNING_RKNN_THREADS` is set to 3, it will be somewhat faster than ARM NN at FP32, but somewhat slower than ARM NN if `MACHINE_LEARNING_ANN_FP16_TURBO` is enabled
+    - When other tasks also use the GPU (like transcoding), RKNPU has a significant advantage over ARM NN as it uses the otherwise idle NPU instead of competing for GPU usage
+  - Lower RAM usage if `MACHINE_LEARNING_RKNN_THREADS` is at the default of 1, but significantly higher if greater than 1 (which is necessary for it to fully utilize the NPU and hence be comparable in speed to ARM NN)