# Introducing the AMD 5th Gen EPYC™ CPU

DevFeed: [Introducing the AMD 5th Gen EPYC™ CPU](<https://devfeed.tech/articles/introducing-the-amd-5th-gen-epyctm-cpu-7246.md>)

Original publisher: [Read original article](<https://huggingface.co/blog/huggingface-amd-turin>)

Author: Mohit Sharma; Morgan Funtowicz

Published: 2024-10-10T00:00:00Z

Content type: article

Language: en

Sources: [Hugging Face - Blog](<https://devfeed.tech/sources/hugging-face-blog.md>)

Topics: [cpu](<https://devfeed.tech/topics/cpu.md>), [LLM evaluation / benchmarking](<https://devfeed.tech/topics/llm-evaluation-benchmarking.md>), [Inference](<https://devfeed.tech/topics/inference.md>), [hugging face](<https://devfeed.tech/topics/hugging-face.md>), [LLMs](<https://devfeed.tech/topics/llms.md>), [Keras](<https://devfeed.tech/topics/keras.md>)

Tags: [amd](<https://devfeed.tech/tags/amd.md>), [benchmarking](<https://devfeed.tech/tags/benchmarking.md>), [benchmarks](<https://devfeed.tech/tags/benchmarks.md>), [cpu](<https://devfeed.tech/tags/cpu.md>), [ecosystem](<https://devfeed.tech/tags/ecosystem.md>), [inference](<https://devfeed.tech/tags/inference.md>), [llama](<https://devfeed.tech/tags/llama.md>), [llm](<https://devfeed.tech/tags/llm.md>), [llms](<https://devfeed.tech/tags/llms.md>), [meta](<https://devfeed.tech/tags/meta.md>), [model](<https://devfeed.tech/tags/model.md>), [models](<https://devfeed.tech/tags/models.md>), [optimum](<https://devfeed.tech/tags/optimum.md>), [performance](<https://devfeed.tech/tags/performance.md>), [pytorch](<https://devfeed.tech/tags/pytorch.md>), [speed](<https://devfeed.tech/tags/speed.md>), [text-generation](<https://devfeed.tech/tags/text-generation.md>), [tokens](<https://devfeed.tech/tags/tokens.md>)

## AI overview

Hugging Face evaluates AMD's 5th Gen EPYC CPUs, Turin and Genoa, for large language model and RAG workloads. The article presents benchmark results using PyTorch inference optimizations and multiple Meta LLaMA 3.1 8B instances across summarization, chatbot, translation, essay writing, and live captioning, comparing decode throughput at different batch sizes.

## Source excerpt

We're on a journey to advance and democratize artificial intelligence through open source and open science.