Intel Arc B580 vs. AMD Radeon RX 9000 vs. NVIDIA RTX 50 Series For Llama.cpp Vulkan Performance

Written by Michael Larabel in Display Drivers on 8 December 2025 at 10:50 AM EST. Page 3 of 5. 11 Comments.
Llama.cpp benchmark with settings of Backend: Vulkan, Model: granite-3.0-3b-a800m-instruct-Q8_0, Test: Text Generation 128. RTX 5090 was the fastest.
Llama.cpp benchmark with settings of Backend: Vulkan, Model: granite-3.0-3b-a800m-instruct-Q8_0, Test: Prompt Processing 2048. RTX 5090 was the fastest.
Llama.cpp benchmark with settings of Backend: Vulkan, Model: granite-3.0-3b-a800m-instruct-Q8_0, Test: Prompt Processing 2048. RTX 5090 was the fastest.
Llama.cpp benchmark with settings of Backend: Vulkan, Model: granite-3.0-3b-a800m-instruct-Q8_0, Test: Prompt Processing 2048. RTX 5090 was the fastest.
Llama.cpp benchmark with settings of Backend: Vulkan, Model: granite-3.0-3b-a800m-instruct-Q8_0, Test: Prompt Processing 2048. RTX 5090 was the fastest.

With Granite 3.0 3B the NVIDIA graphics cards with Llama.cpp's Vulkan back-end were delivering much better performance than the Intel hardware on the ANV driver and the RDNA4 GPUs on RADV.

Llama.cpp benchmark with settings of Backend: Vulkan, Model: Mistral-7B-Instruct-v0.3-Q8_0, Test: Text Generation 128. RTX 5090 was the fastest.
Llama.cpp benchmark with settings of Backend: Vulkan, Model: Mistral-7B-Instruct-v0.3-Q8_0, Test: Prompt Processing 512. RTX 5090 was the fastest.
Llama.cpp benchmark with settings of Backend: Vulkan, Model: Mistral-7B-Instruct-v0.3-Q8_0, Test: Prompt Processing 1024. RTX 5090 was the fastest.
Llama.cpp benchmark with settings of Backend: Vulkan, Model: Mistral-7B-Instruct-v0.3-Q8_0, Test: Prompt Processing 2048. RTX 5090 was the fastest.
Llama.cpp benchmark with settings of Backend: Vulkan, Model: Mistral-7B-Instruct-v0.3-Q8_0, Test: Prompt Processing 2048. RTX 5090 was the fastest.
Llama.cpp benchmark with settings of Backend: Vulkan, Model: Mistral-7B-Instruct-v0.3-Q8_0, Test: Prompt Processing 2048. RTX 5090 was the fastest.
Llama.cpp benchmark with settings of Backend: Vulkan, Model: Mistral-7B-Instruct-v0.3-Q8_0, Test: Prompt Processing 2048. RTX 5090 was the fastest.

The results aren't too surprising albeit useful having some fresh figures to share for those curious and satisfying a Phoronix Premium supporter's request.

Related Articles
AMD Boosting AI/LLM Performance For Radeon iGPUs As Much As 18~23% With Linux 7.4
The Performance Benefits To Upgrading Mesa With Intel Arc B390 On Ubuntu Linux
Nouveau vs. NVIDIA R610 On CachyOS With The GeForce RTX 5090 Laptop GPU
Intel Arc Pro B70 Showing Off Some Performance Wins With Linux 7.1
Linux 7.1 Helping Intel Arc Battlemage Graphics Achieve Better Performance
ROCm 7.0.0 vs. ROCm 7.2.3 Performance On The AMD Radeon AI PRO R9700