Latest Open-Source AMD Improvements Allowing For Better Llama.cpp AI Performance Against Windows 11

Written by Michael Larabel in Software on 17 September 2025 at 10:48 AM EDT. Page 3 of 5. 21 Comments.

👁 Llama.cpp benchmark with settings of Backend: Vulkan, Model: Mistral-7B-Instruct-v0.3-Q8_0, Test: Text Generation 128. Linux 6.17 + Mesa 25.3-dev was the fastest.

👁 Llama.cpp benchmark with settings of Backend: Vulkan, Model: Mistral-7B-Instruct-v0.3-Q8_0, Test: Prompt Processing 512. Linux 6.17 + Mesa 25.3-dev was the fastest.

👁 Llama.cpp benchmark with settings of Backend: Vulkan, Model: Mistral-7B-Instruct-v0.3-Q8_0, Test: Prompt Processing 1024. Linux 6.17 + Mesa 25.3-dev was the fastest.

👁 Llama.cpp benchmark with settings of Backend: Vulkan, Model: DeepSeek-R1-Distill-Llama-8B-Q8_0, Test: Text Generation 128. Linux 6.17 + Mesa 25.3-dev was the fastest.

👁 Llama.cpp benchmark with settings of Backend: Vulkan, Model: granite-3.0-3b-a800m-instruct-Q8_0, Test: Text Generation 128. Windows 11 25H2 was the fastest.

👁 Llama.cpp benchmark with settings of Backend: Vulkan, Model: DeepSeek-R1-Distill-Llama-8B-Q8_0, Test: Prompt Processing 512. Windows 11 25H2 was the fastest.

👁 Llama.cpp benchmark with settings of Backend: Vulkan, Model: DeepSeek-R1-Distill-Llama-8B-Q8_0, Test: Prompt Processing 1024. Linux 6.17 + Mesa 25.3-dev was the fastest.

👁 Llama.cpp benchmark with settings of Backend: Vulkan, Model: granite-3.0-3b-a800m-instruct-Q8_0, Test: Prompt Processing 512. Windows 11 25H2 was the fastest.

👁 Llama.cpp benchmark with settings of Backend: Vulkan, Model: granite-3.0-3b-a800m-instruct-Q8_0, Test: Prompt Processing 1024. Windows 11 25H2 was the fastest.

For those with AMD Radeon graphics and wanting to explore Vulkan-accelerated Llama.cpp, it definitely pays off moving to the very latest open-source driver code compared to what is shipped by the likes of Ubuntu 24.04.3 LTS / Ubuntu 25.04. There still are gaps in some area but overall there was a huge uplift moving to Linux 6.17 and Mesa 25.3.

21 Comments - Next Page

Page: 1 2 3 4 5 Next Page

URL: https://www.phoronix.com/review/llama-cpp-windows-linux/3

⇱ Latest Open-Source AMD Improvements Allowing For Better Llama.cpp AI Performance Against Windows 11 - Phoronix

Latest Open-Source AMD Improvements Allowing For Better Llama.cpp AI Performance Against Windows 11