Llama3bench
AMD Ryzen Threadripper 2990WX 32-Core testing with a ASRock X399 Phantom Gaming 6 (P1.10 BIOS) and AMD Radeon 540/540X/550/550X / RX 540X/550/550X 2GB on AlmaLinux 9.5 via the Phoronix Test Suite.


LLama3bench1: 

	Processor: AMD Ryzen Threadripper 2990WX 32-Core @ 3.00GHz (32 Cores / 64 Threads), Motherboard: ASRock X399 Phantom Gaming 6 (P1.10 BIOS), Chipset: AMD 17h, Memory: 128GB, Disk: 1024GB INTEL SSDPEKNW010T8, Graphics: AMD Radeon 540/540X/550/550X / RX 540X/550/550X 2GB (1183/1500MHz), Audio: Realtek ALC1220, Monitor: PHL 273B9, Network: Intel I211 + Realtek RTL8125 2.5GbE

	OS: AlmaLinux 9.5, Kernel: 5.14.0-503.14.1.el9_5.x86_64 (x86_64), Desktop: GNOME Shell 40.10, Display Server: X Server, Compiler: GCC 11.5.0 20240719, File-System: xfs, Screen Resolution: 1920x1080


Llama.cpp b4154
Backend: CPU BLAS - Model: Llama-3.1-Tulu-3-8B-Q8_0 - Test: Text Generation 128
Tokens Per Second > Higher Is Better
LLama3bench1 . 2.75 |==========================================================


Llama.cpp b4154
Backend: CPU BLAS - Model: Llama-3.1-Tulu-3-8B-Q8_0 - Test: Prompt Processing 512
Tokens Per Second > Higher Is Better
LLama3bench1 . 4.18 |==========================================================


Llama.cpp b4154
Backend: CPU BLAS - Model: Llama-3.1-Tulu-3-8B-Q8_0 - Test: Prompt Processing 1024
Tokens Per Second > Higher Is Better
LLama3bench1 . 4.20 |==========================================================


Llama.cpp b4154
Backend: CPU BLAS - Model: Llama-3.1-Tulu-3-8B-Q8_0 - Test: Prompt Processing 2048
Tokens Per Second > Higher Is Better
LLama3bench1 . 4.14 |==========================================================