Gemma 3n — Local AI Model by Google DeepMind

作者： Jakub Rusinowski · 最后更新： 2026年7月30日

Google移动优先的多模态模型系列。采用MatFormer嵌套架构——单个模型文件包含多个可按不同规格运行的子模型。处理文本、图像、音频和视频。无需联网即可在手机上运行。

Hardware Requirements

Gemma 3n E2BMin 2 GB VRAM · Q4_K_M · 32,768 ctx · ollama run gemma3n:e2b
Gemma 3n E4BMin 3 GB VRAM · Q4_K_M · 32,768 ctx · ollama run gemma3n:e4b

Recommended GPU

The cheapest GPU that runs Gemma 3n locally (min 2 GB VRAM) is the Intel Arc B570 (10 GB).

联盟营销声明: 本页部分链接为联盟推广链接——如果你通过它们购买，LLM Configurator 可能会获得佣金，而你无需支付任何额外费用。作为亚马逊联盟成员（Amazon Associate），LLM Configurator 会从符合条件的购买中获得收益。
Intel Arc B570 10GB
首发建议零售价：$219
2026年价格波动较大——请以当前商品页价格为准。
在亚马逊查看价格

How to Run Locally

Install Ollama then run: ollama run gemma3n:e2b

Minimum VRAM: 2 GB. For best results use Q4_K_M quantization.

Gemma 3n — Frequently Asked Questions

How much VRAM does Gemma 3n need?

Gemma 3n needs about 2 GB VRAM at Q4_K_M quantization for its smallest variant. Variants: Gemma 3n E2B (2 GB, Q4_K_M); Gemma 3n E4B (3 GB, Q4_K_M). On Apple Silicon, unified memory counts toward this requirement.

Can I run Gemma 3n on an RTX 4090 (24 GB)?

Yes — Gemma 3n runs on an RTX 4090 (24 GB) and other 24 GB cards such as the RTX 3090. Smaller variants also fit comfortably on 8–16 GB GPUs at Q4_K_M.

What quantization should I use for Gemma 3n?

Q4_K_M is the best balance of quality and VRAM for Gemma 3n in most cases. Choose Q8_0 for near-lossless quality if you have spare VRAM, or smaller quants (Q3/Q2) only when memory is tight.

How do I run Gemma 3n with Ollama?

Install Ollama, then run: ollama run gemma3n:e2b. This downloads Gemma 3n and starts a local, OpenAI-compatible endpoint — no internet connection is needed after the initial download.