> For the complete documentation index, see [llms.txt](https://docs.maiagent.ai/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.maiagent.ai/tech/ja/platform-development/gpu.md).

# GPU 計算リソースのハードウェア計画

## GPU における Llama3 の推論速度（token/秒）

<figure><img src="https://605688223-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FVYMUz6J7vDZ0QTvb1rbN%2Fuploads%2Fgit-blob-48ab072976455e9efd6b67df1b515038a3732e43%2Foutput%20(4).png?alt=media" alt=""><figcaption><p>主要な GPU における Llama3 8B / 70B の性能比較</p></figcaption></figure>

<table><thead><tr><th width="166">GPU</th><th width="145">メモリ(VRAM)</th><th width="125">8B Q4_K_M</th><th width="89">8B F16</th><th width="129">70B Q4_K_M</th><th width="159">70B F16</th></tr></thead><tbody><tr><td>RTX 4090</td><td>24GB</td><td>127.74</td><td>54.34</td><td>メモリ超過</td><td>メモリ超過</td></tr><tr><td>RTX A6000</td><td>48GB</td><td>102.22</td><td>40.25</td><td>14.58</td><td>メモリ超過</td></tr><tr><td>L40S</td><td>48GB</td><td>113.60</td><td>43.42</td><td>15.31</td><td>メモリ超過</td></tr><tr><td>RTX 6000 Ada</td><td>48GB</td><td>130.99</td><td>51.97</td><td>18.36</td><td>メモリ超過</td></tr><tr><td>A100</td><td>80GB</td><td>138.31</td><td>54.56</td><td>22.11</td><td>メモリ超過</td></tr><tr><td>H100</td><td>80GB</td><td>144.49</td><td>67.79</td><td>25.01</td><td>メモリ超過</td></tr><tr><td>M2 Ultra</td><td>192GB</td><td>76.28</td><td>36.25</td><td>12.13</td><td>4.71</td></tr></tbody></table>

***

## Llama3 モデルが必要とする VRAM

| モデル        | Q4\_K\_M（量子化後） | F16（オリジナル） |
| ---------- | -------------- | ---------- |
| Llama3 8B  | 4.58 GB        | 14.96 GB   |
| Llama3 70B | 39.59 GB       | 131.42 GB  |

データ出典

{% embed url="<https://github.com/XiongjieDai/GPU-Benchmarks-on-LLM-Inference>" %}

***

## ハードウェア構成の推奨

MaiAgent は各種 Nvidia GPU に対応しています。

<table><thead><tr><th width="330.84375">名称</th><th>VRAM</th></tr></thead><tbody><tr><td>NVIDIA H200</td><td>141 GB</td></tr><tr><td>NVIDIA RTX PRO 6000 Blackwell</td><td>96 GB</td></tr><tr><td>NVIDIA H100</td><td>80 GB</td></tr><tr><td>RTX 6000 Ada</td><td>48 GB</td></tr><tr><td>NVIDIA A100</td><td>80GB</td></tr><tr><td>NVIDIA L40S</td><td>48 GB</td></tr></tbody></table>

より詳しい情報が必要な場合は、MaiAgent の専門コンサルタントへお気軽にご相談ください。<mark style="color:blue;"><sales@maiagent.ai></mark> までメールにてお問い合わせください。


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters:

```
GET https://docs.maiagent.ai/tech/ja/platform-development/gpu.md?ask=<question>&goal=<user_goal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `build a script that syncs our docs to a CMS` lets GitBook tailor the answer to that use case.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.