For the LLM model the Alibaba’s Qwen 3.6 27B with different quantization are used to show the difference in token generation per second and memory…
Tag: llama-bench
llama-bench the LLama 4 Scout 17B 16E and AMD EPYC 9554 CPU
This article shows the CPU-only inference with a modern server processor – AMD Epyc 9554. For the LLM model the Meta’s Llama 4 Scout 17B…
llama-bench the Phi-4 14B and AMD EPYC 9554 CPU
This article shows the CPU-only inference with a modern server processor – AMD Epyc 9554. For the LLM model the Microsoft’s Phi-4 14B with different…
llama-bench the Gemma 3 27B and AMD EPYC 9554 CPU
This article shows the CPU-only inference with a modern server processor – AMD Epyc 9554. For the LLM model the Google’s Gemma 3 27B Instruct…