Skip to content
This page is not translated yet — showing the original. We never ship machine translation as a placeholder.
Needs a toolchainLlama 3.3 Community License Tested

Llama 3.3 70B Instruct

In one line:Llama 3.3 70B Instruct 是一个需要 48GB 级显存的大家伙:本地能力的之一,能。

需要 48GB 级显存的大家伙:本地能力的天花板之一。

Official source

We host and mirror nothing — the official page is the source of truth.

Official icon for Llama 3.3 70B Instruct Metahttps://github.com/meta-llama/llama-modelsOpen official page
Official sourceYou are leaving AIWorksWell for Meta. That site is not under our control; its content, privacy and security are its own responsibility. Please judge for yourself.

Install prompt

Copy it, paste it into your AI (Claude Code, Codex, ChatGPT…), and it installs and verifies for you.

44 lines
我需要你帮我在我的机器上安装并运行一个软件。

【软件信息】
名称:Llama 3.3 70B Instruct
用途:需要 48GB 级显存的大家伙:本地能力的天花板之一。
官方来源:https://github.com/meta-llama/llama-models
许可:Llama 3.3 Community License
Scroll inside the box with your mouse wheel — copying still gives you the full prompt1267 chars

Copy → paste into your own AI → it installs for you

Contact the original author (Meta)

Bugs in the software itself go to the author's own official channel — that is where they actually receive them. We pass things on; we do not answer for the author.

Install failed?

Paste the raw error — once triaged and verified it is written back here, so the next person's AI avoids it. No login needed.

About this entry

它是什么

70B 级稠密模型的定位很清楚:能力接近云端大模型,但门槛也在那里——量化后仍需 40GB 以上可用显存,普通消费级显卡单人基本跑不动。来源:https://github.com/meta-llama/llama-modelshttps://github.com/meta-llama/llama-models

怎么用起来

两条现实路径:① 多卡/大显存工作站(48GB+);② 走在线 API。Mac Studio 等大统一内存机型也可以,但速度取决于内存带宽。来源:https://github.com/meta-llama/llama-modelshttps://github.com/meta-llama/llama-models

以上坑来自 https://github.com/meta-llama/llama-modelshttps://github.com/meta-llama/llama-models 与官方文档。

来源与署名

Mentioned from:https://github.com/meta-llama/llama-modelshttps://github.com/meta-llama/llama-models · 原作者 Meta(Llama 3.3 Community License)。

Summary for AI

Llama 3.3 70B Instruct 是 Meta 的大参数指令模型,需要 48GB 级显存,属于本地可跑模型里能力较强的一档,许可为 Llama 3.3 Community License。

A self-contained answer paragraph — this is the part AI search quotes. · Page reviewed 2026-10-06

FAQ

要多大显存?

48GB 级显存起步,量化后可降低需求。

许可是什么?

Llama 3.3 Community License,商用前请核对条款。

Pitfalls / known issues

All recorded from real installs, and injected into the prompt above.

  • •下载体积 80GB 级,先确认磁盘空间。
  • •40GB 显存以下不要指望"凑合跑"——量化到 Q2 会明显降智,不如直接用更小的模型。

You might also like

We store, mirror and repackage nothing. Every install path points to the author’s own official page.

Nothing here has been reviewed by an app store. Judge the source and licence yourself; you install at your own risk.