NVIDIA RTX PRO Blackwell Performance Delivering Excellent Linux Performance

Written by Michael Larabel in Graphics Cards on 21 May 2026 at 11:43 AM EDT. Page 4 of 9. 33 Comments.

👁 Llama.cpp benchmark with settings of Backend: GPU, Model: DeepSeek-R1-Distill-Llama-8B-Q8_0, Test: Prompt Processing 512. RTX PRO 6000 Blackwell was the fastest.

👁 Llama.cpp benchmark with settings of Backend: GPU, Model: DeepSeek-R1-Distill-Llama-8B-Q8_0, Test: Prompt Processing 2048. RTX PRO 6000 Blackwell was the fastest.

👁 Llama.cpp benchmark with settings of Backend: GPU, Model: GLM-4.7-Flash-IQ4_XS, Test: Text Generation 128. RTX PRO 6000 Blackwell was the fastest.

👁 Llama.cpp benchmark with settings of Backend: GPU, Model: GLM-4.7-Flash-IQ4_XS, Test: Prompt Processing 512. RTX PRO 6000 Blackwell was the fastest.

👁 Llama.cpp benchmark with settings of Backend: GPU, Model: GLM-4.7-Flash-IQ4_XS, Test: Prompt Processing 2048. RTX PRO 6000 Blackwell was the fastest.

Even with the NVIDIA RTX Ada Generation graphics cards the RTX 6000 Ada Generation was already well outpacing the Radeon AI PRO R9700 and Arc Pro B70. Now that I have my hands on the NVIDIA RTX PRO Blackwell we see just how far these new NVIDIA wares come in delivering incredible performance in a class of its own.

👁 Llama.cpp benchmark with settings of Backend: Vulkan, Model: Llama-3.1-Tulu-3-8B-Q8_0, Test: Text Generation 128. RTX PRO 6000 Blackwell was the fastest.

👁 Llama.cpp benchmark with settings of Backend: Vulkan, Model: Llama-3.1-Tulu-3-8B-Q8_0, Test: Prompt Processing 512. RTX PRO 6000 Blackwell was the fastest.

👁 Llama.cpp benchmark with settings of Backend: Vulkan, Model: Llama-3.1-Tulu-3-8B-Q8_0, Test: Prompt Processing 2048. RTX PRO 6000 Blackwell was the fastest.

👁 Llama.cpp benchmark with settings of Backend: Vulkan, Model: granite-3.0-3b-a800m-instruct-Q8_0, Test: Text Generation 128. RTX PRO 6000 Blackwell was the fastest.

👁 Llama.cpp benchmark with settings of Backend: Vulkan, Model: granite-3.0-3b-a800m-instruct-Q8_0, Test: Prompt Processing 512. RTX PRO 6000 Blackwell 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 PRO 6000 Blackwell was the fastest.

When turning to the common Vulkan API back-end of Llama.cpp that can run across all the GPU vendors, NVIDIA continued to dominate with terrific gen-on-gen performance and relative to the graphics cards from competing vendors.

👁 Llama.cpp benchmark with settings of Backend: Vulkan, Model: Mistral-7B-Instruct-v0.3-Q8_0, Test: Text Generation 128. RTX PRO 6000 Blackwell was the fastest.

👁 Llama.cpp benchmark with settings of Backend: Vulkan, Model: Mistral-7B-Instruct-v0.3-Q8_0, Test: Prompt Processing 512. RTX PRO 6000 Blackwell was the fastest.

👁 Llama.cpp benchmark with settings of Backend: Vulkan, Model: Mistral-7B-Instruct-v0.3-Q8_0, Test: Prompt Processing 2048. RTX PRO 6000 Blackwell was the fastest.

👁 Llama.cpp benchmark with settings of Backend: Vulkan, Model: gpt-oss-20b-Q8_0, Test: Text Generation 128. RTX PRO 6000 Blackwell was the fastest.

👁 Llama.cpp benchmark with settings of Backend: Vulkan, Model: gpt-oss-20b-Q8_0, Test: Prompt Processing 512. RTX PRO 6000 Blackwell was the fastest.

👁 Llama.cpp benchmark with settings of Backend: Vulkan, Model: gpt-oss-20b-Q8_0, Test: Prompt Processing 2048. RTX PRO 6000 Blackwell was the fastest.

👁 Llama.cpp benchmark with settings of Backend: Vulkan, Model: DeepSeek-R1-Distill-Llama-8B-Q8_0, Test: Prompt Processing 2048. RTX PRO 6000 Blackwell was the fastest.

Not only was the NVIDIA RTX PRO Blackwell line-up delivering the best raw performance but on a performance-per-Watt basis it was class leading too and building off the previously-leading RTX Ada Generation power efficiency.

33 Comments - Next Page

Page: 1 2 3 4 5 6 7 8 9 Next Page

URL: https://www.phoronix.com/review/nvidia-rtx-pro-blackwell/4

⇱ NVIDIA RTX PRO Blackwell Performance Delivering Excellent Linux Performance Review - Phoronix

NVIDIA RTX PRO Blackwell Performance Delivering Excellent Linux Performance