---
title: "Discussion on \"I cut EmbeddingGemma 2's vectors to a sixth of their size. It got more answers right, and that was the worrying part.\" | Hashnode"
description: "Discussion on \"I cut EmbeddingGemma 2's vectors to a sixth of their size. It got more answers right, and that was the worrying part.\". What EmbeddingGemma 2 is, what Google says it can do, and a MacBook Air test of search by meaning, pictures, shorter vectors and speed."
url: "https://hashnode.com/posts/i-cut-embeddinggemma-2s-vectors-to-a-sixth-of-their-size-it-got-more-answers-right-and-that-was-the-/6ad03ab8b8db4be913f902a7"
---

[Feed](https://hashnode.com/feed) /

Discussion

# [I cut EmbeddingGemma 2's vectors to a sixth of their size. It got more answers right, and that was the worrying part.](https://systemdesignacademy.hashnode.dev/i-cut-embeddinggemma-2s-vectors-to-a-sixth-of-their-size-it-got-more-answers-right-and-that-was-the-?utm_source=hashnode&utm_medium=feed)

What EmbeddingGemma 2 is, what Google says it can do, and a MacBook Air test of search by meaning, pictures, shorter vectors and speed.

Oct 15 · 17 min read · systemdesignacademy.hashnode.dev  
Read the article

-   [#google](https://hashnode.com/tag/google)
-   [#embedding](https://hashnode.com/tag/embedding)
-   [#machine-learning](https://hashnode.com/tag/machine-learning)
-   [#artificial-intelligence](https://hashnode.com/tag/artificial-intelligence)
-   [#semantic-search](https://hashnode.com/tag/semantic-search)

## Written by

[RONI DAS](https://hashnode.com/@ronidas)

@ronidas · India

  
[View profile](https://hashnode.com/@ronidas)

AI engineering, agentic memory, machine learning, and system design at scale.

I work on AI systems and the infrastructure they actually run on: agentic architectures, memory for agents, retrieval, and the graph and data layers that keep model output grounded in something real. Formerly at Neo4j. I also write and teach the systems side that most AI content skips, from distributed systems and databases to the design decisions that decide whether a model ever reaches production. I run Total Technology Zonne on YouTube and I am building systemdesign.academy, an interactive course on system design, machine learning, and AI engineering, covering the parts most tutorials leave as an exercise for the reader. Mock interviews and prep packs: topmate.io/roni

## Responses

Markdown supported · ⌘↵ to post

No responses yet.