ryzen 5950x llama-cpp
AMD Ryzen 9 5950X 16-Core testing with a MSI B550 GAMING GEN3 (MS-7B86) v5.0 (P.91 BIOS) and XFX AMD Radeon RX 6750 XT 12GB on Ubuntu 24.04 via the Phoronix Test Suite.


AMD Ryzen 9 5950X 16-Core - XFX AMD Radeon RX 6750 XT: 

	Processor: AMD Ryzen 9 5950X 16-Core @ 3.40GHz (16 Cores / 32 Threads), Motherboard: MSI B550 GAMING GEN3 (MS-7B86) v5.0 (P.91 BIOS), Chipset: AMD Starship/Matisse, Memory: 4 x 32GB DDR4-3600MT/s CMK64GX4M2D3600C18, Disk: 2000GB CT2000P3PSSD8, Graphics: XFX AMD Radeon RX 6750 XT 12GB, Audio: AMD Navi 21/23, Monitor: XV271U M3, Network: Realtek RTL8111/8168/8211/8411 + Intel Wi-Fi 6 AX200

	OS: Ubuntu 24.04, Kernel: 6.8.0-51-generic (x86_64), Desktop: GNOME Shell 46.0, Display Server: X Server 1.21.1.11 + Wayland, OpenGL: 4.6 Mesa 24.2.0-devel (LLVM 18.1.7 DRM 3.58), OpenCL: OpenCL 2.1 AMD-APP (3625.0), Compiler: GCC 13.3.0, File-System: ext4, Screen Resolution: 2560x1440


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 5950X 16-Core - XFX AMD Radeon RX 6750 XT . 208.41 |===============


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 5950X 16-Core - XFX AMD Radeon RX 6750 XT . 215.02 |===============


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 5950X 16-Core - XFX AMD Radeon RX 6750 XT . 222.60 |===============


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 5950X 16-Core - XFX AMD Radeon RX 6750 XT . 44.17 |================


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 5950X 16-Core - XFX AMD Radeon RX 6750 XT . 48.36 |================


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 5950X 16-Core - XFX AMD Radeon RX 6750 XT . 48.36 |================


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 5950X 16-Core - XFX AMD Radeon RX 6750 XT . 48.08 |================


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 5950X 16-Core - XFX AMD Radeon RX 6750 XT . 6.28 |=================


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 5950X 16-Core - XFX AMD Radeon RX 6750 XT . 48.03 |================


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 5950X 16-Core - XFX AMD Radeon RX 6750 XT . 48.58 |================


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 5950X 16-Core - XFX AMD Radeon RX 6750 XT . 48.41 |================


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 5950X 16-Core - XFX AMD Radeon RX 6750 XT . 6.02 |=================