# Running Gemma 4 26B at 5 Tokens/Sec on a 13-Year-Old Xeon With No GPU

DevFeed: [Running Gemma 4 26B at 5 Tokens/Sec on a 13-Year-Old Xeon With No GPU](<https://devfeed.tech/articles/running-gemma-4-26b-at-5-tokens-sec-on-a-13-year-old-xeon-with-no-gpu-56106.md>)

Original publisher: [Read original article](<https://www.developersdigest.tech/blog/gemma-4-26b-old-xeon-no-gpu>)

Author: Developers Digest

Published: 2026-07-15T00:00:00Z

Content type: article

Language: en

Sources: [Developers Digest](<https://devfeed.tech/sources/developers-digest.md>)

Topics: [gemma](<https://devfeed.tech/topics/gemma.md>), [Mixture of Experts (MoE)](<https://devfeed.tech/topics/mixture-of-experts-moe.md>), [Inference](<https://devfeed.tech/topics/inference.md>), [Hardware](<https://devfeed.tech/topics/hardware.md>), [Local AI](<https://devfeed.tech/topics/local-ai.md>), [bug](<https://devfeed.tech/topics/bug.md>), [Google](<https://devfeed.tech/topics/google.md>)

Tags: [bug](<https://devfeed.tech/tags/bug.md>), [developer](<https://devfeed.tech/tags/developer.md>), [gemma](<https://devfeed.tech/tags/gemma.md>), [gemma-4](<https://devfeed.tech/tags/gemma-4.md>), [google](<https://devfeed.tech/tags/google.md>), [gpu](<https://devfeed.tech/tags/gpu.md>), [hacker-news](<https://devfeed.tech/tags/hacker-news.md>), [inference](<https://devfeed.tech/tags/inference.md>), [llm](<https://devfeed.tech/tags/llm.md>), [local](<https://devfeed.tech/tags/local.md>), [local-ai](<https://devfeed.tech/tags/local-ai.md>), [moe](<https://devfeed.tech/tags/moe.md>), [news](<https://devfeed.tech/tags/news.md>), [open-source](<https://devfeed.tech/tags/open-source.md>), [running](<https://devfeed.tech/tags/running.md>), [xeon](<https://devfeed.tech/tags/xeon.md>)

## AI overview

A developer ran Google's Gemma 4 26B model on 2013 Xeon hardware without a GPU for under $300. The article discusses a silent Mixture-of-Experts bug whose fix is now upstream and what this means for local inference.

## Source excerpt

A developer got Google's Gemma 4 26B running on 2013 Xeon hardware for under $300. The fix for a silent MoE bug is now upstream - here's what it means for local inference.