aorus-llama-cpp
AMD Ryzen 9 9950X 16-Core testing with a Gigabyte X870 AORUS ELITE WIFI7 (F3h BIOS) and Gigabyte NVIDIA GeForce RTX 4090 24GB on openSUSE Leap 15.6 via the Phoronix Test Suite.


AMD Ryzen 9 9950X 16-Core - Gigabyte NVIDIA GeForce: 

	Processor: AMD Ryzen 9 9950X 16-Core @ 4.30GHz (16 Cores / 32 Threads), Motherboard: Gigabyte X870 AORUS ELITE WIFI7 (F3h BIOS), Chipset: AMD Raphael/Granite, Memory: 4 x 32 GB DDR5-3600MT/s CMH64GX5M2B6000C38, Disk: 1000GB Samsung SSD 970 EVO Plus 1TB + 2 x 2000GB Samsung SSD 870, Graphics: Gigabyte NVIDIA GeForce RTX 4090 24GB, Audio: NVIDIA AD102 HD Audio, Monitor: SyncMaster, Network: Realtek RTL8125 2.5GbE + MEDIATEK Device 7925

	OS: openSUSE Leap 15.6, Kernel: 6.4.0-150600.23.30-default (x86_64), Display Server: X Server 1.21.1.11, Display Driver: NVIDIA, Compiler: GCC 11.3.0 + CUDA 12.6, File-System: btrfs, Screen Resolution: 1280x1024


Llama.cpp b4397
Backend: CPU BLAS - Model: Llama-3.1-Tulu-3-8B-Q8_0 - Test: Text Generation 128
Tokens Per Second > Higher Is Better
AMD Ryzen 9 9950X 16-Core - Gigabyte NVIDIA GeForce . 5.7 |====================


Llama.cpp b4397
Backend: CPU BLAS - Model: Llama-3.1-Tulu-3-8B-Q8_0 - Test: Prompt Processing 512
Tokens Per Second > Higher Is Better
AMD Ryzen 9 9950X 16-Core - Gigabyte NVIDIA GeForce . 29.63 |==================


Llama.cpp b4397
Backend: CPU BLAS - Model: Llama-3.1-Tulu-3-8B-Q8_0 - Test: Prompt Processing 1024
Tokens Per Second > Higher Is Better
AMD Ryzen 9 9950X 16-Core - Gigabyte NVIDIA GeForce . 31.09 |==================


Llama.cpp b4397
Backend: CPU BLAS - Model: Llama-3.1-Tulu-3-8B-Q8_0 - Test: Prompt Processing 2048
Tokens Per Second > Higher Is Better
AMD Ryzen 9 9950X 16-Core - Gigabyte NVIDIA GeForce . 31.85 |==================


Llama.cpp b4397
Backend: NVIDIA CUDA - Model: Llama-3.1-Tulu-3-8B-Q8_0 - Test: Text Generation 128
Tokens Per Second > Higher Is Better
AMD Ryzen 9 9950X 16-Core - Gigabyte NVIDIA GeForce . 100.83 |=================


Llama.cpp b4397
Backend: CPU BLAS - Model: Mistral-7B-Instruct-v0.3-Q8_0 - Test: Text Generation 128
Tokens Per Second > Higher Is Better
AMD Ryzen 9 9950X 16-Core - Gigabyte NVIDIA GeForce . 6.02 |===================


Llama.cpp b4397
Backend: NVIDIA CUDA - Model: Llama-3.1-Tulu-3-8B-Q8_0 - Test: Prompt Processing 512
Tokens Per Second > Higher Is Better
AMD Ryzen 9 9950X 16-Core - Gigabyte NVIDIA GeForce . 11536.45 |===============


Llama.cpp b4397
Backend: NVIDIA CUDA - Model: Llama-3.1-Tulu-3-8B-Q8_0 - Test: Prompt Processing 1024
Tokens Per Second > Higher Is Better
AMD Ryzen 9 9950X 16-Core - Gigabyte NVIDIA GeForce . 10755.70 |===============


Llama.cpp b4397
Backend: NVIDIA CUDA - Model: Llama-3.1-Tulu-3-8B-Q8_0 - Test: Prompt Processing 2048
Tokens Per Second > Higher Is Better
AMD Ryzen 9 9950X 16-Core - Gigabyte NVIDIA GeForce . 9540.82 |================


Llama.cpp b4397
Backend: CPU BLAS - Model: Mistral-7B-Instruct-v0.3-Q8_0 - Test: Prompt Processing 512
Tokens Per Second > Higher Is Better
AMD Ryzen 9 9950X 16-Core - Gigabyte NVIDIA GeForce . 29.62 |==================


Llama.cpp b4397
Backend: CPU BLAS - Model: Mistral-7B-Instruct-v0.3-Q8_0 - Test: Prompt Processing 1024
Tokens Per Second > Higher Is Better
AMD Ryzen 9 9950X 16-Core - Gigabyte NVIDIA GeForce . 30.91 |==================


Llama.cpp b4397
Backend: CPU BLAS - Model: Mistral-7B-Instruct-v0.3-Q8_0 - Test: Prompt Processing 2048
Tokens Per Second > Higher Is Better
AMD Ryzen 9 9950X 16-Core - Gigabyte NVIDIA GeForce . 32.02 |==================


Llama.cpp b4397
Backend: NVIDIA CUDA - Model: Mistral-7B-Instruct-v0.3-Q8_0 - Test: Text Generation 128
Tokens Per Second > Higher Is Better
AMD Ryzen 9 9950X 16-Core - Gigabyte NVIDIA GeForce . 105.74 |=================


Llama.cpp b4397
Backend: CPU BLAS - Model: granite-3.0-3b-a800m-instruct-Q8_0 - Test: Text Generation 128
Tokens Per Second > Higher Is Better
AMD Ryzen 9 9950X 16-Core - Gigabyte NVIDIA GeForce . 42.74 |==================


Llama.cpp b4397
Backend: NVIDIA CUDA - Model: Mistral-7B-Instruct-v0.3-Q8_0 - Test: Prompt Processing 512
Tokens Per Second > Higher Is Better
AMD Ryzen 9 9950X 16-Core - Gigabyte NVIDIA GeForce . 11646.75 |===============


Llama.cpp b4397
Backend: NVIDIA CUDA - Model: Mistral-7B-Instruct-v0.3-Q8_0 - Test: Prompt Processing 1024
Tokens Per Second > Higher Is Better
AMD Ryzen 9 9950X 16-Core - Gigabyte NVIDIA GeForce . 10797.67 |===============


Llama.cpp b4397
Backend: NVIDIA CUDA - Model: Mistral-7B-Instruct-v0.3-Q8_0 - Test: Prompt Processing 2048
Tokens Per Second > Higher Is Better
AMD Ryzen 9 9950X 16-Core - Gigabyte NVIDIA GeForce . 9555.98 |================


Llama.cpp b4397
Backend: CPU BLAS - Model: granite-3.0-3b-a800m-instruct-Q8_0 - Test: Prompt Processing 512
Tokens Per Second > Higher Is Better
AMD Ryzen 9 9950X 16-Core - Gigabyte NVIDIA GeForce . 48.71 |==================


Llama.cpp b4397
Backend: CPU BLAS - Model: granite-3.0-3b-a800m-instruct-Q8_0 - Test: Prompt Processing 1024
Tokens Per Second > Higher Is Better
AMD Ryzen 9 9950X 16-Core - Gigabyte NVIDIA GeForce . 51.51 |==================


Llama.cpp b4397
Backend: CPU BLAS - Model: granite-3.0-3b-a800m-instruct-Q8_0 - Test: Prompt Processing 2048
Tokens Per Second > Higher Is Better
AMD Ryzen 9 9950X 16-Core - Gigabyte NVIDIA GeForce . 52.34 |==================


Llama.cpp b4397
Backend: NVIDIA CUDA - Model: granite-3.0-3b-a800m-instruct-Q8_0 - Test: Text Generation 128
Tokens Per Second > Higher Is Better
AMD Ryzen 9 9950X 16-Core - Gigabyte NVIDIA GeForce . 137.78 |=================


Llama.cpp b4397
Backend: NVIDIA CUDA - Model: granite-3.0-3b-a800m-instruct-Q8_0 - Test: Prompt Processing 512
Tokens Per Second > Higher Is Better
AMD Ryzen 9 9950X 16-Core - Gigabyte NVIDIA GeForce . 4793.60 |================


Llama.cpp b4397
Backend: NVIDIA CUDA - Model: granite-3.0-3b-a800m-instruct-Q8_0 - Test: Prompt Processing 1024
Tokens Per Second > Higher Is Better
AMD Ryzen 9 9950X 16-Core - Gigabyte NVIDIA GeForce . 4752.53 |================


Llama.cpp b4397
Backend: NVIDIA CUDA - Model: granite-3.0-3b-a800m-instruct-Q8_0 - Test: Prompt Processing 2048
Tokens Per Second > Higher Is Better
AMD Ryzen 9 9950X 16-Core - Gigabyte NVIDIA GeForce . 4573.06 |================