Alpindale: Goliath 120B

This model is no longer available.

Add AI to your application with Puter.js.

Explore Other Models

Model Card

Goliath 120B is a community-created large language model built by Alpindale by merging two fine-tuned Llama-2 70B models — Xwin and Euryale — into a single 120-billion-parameter model using the mergekit framework.

It was one of the earliest and most notable examples of the model-merging technique in the open-source LLM community, demonstrating that interleaving layers from two complementary fine-tunes could produce a capable larger model without traditional training. It supports Vicuna and Alpaca prompt formats, with Vicuna generally recommended.

Goliath 120B is primarily suited for creative writing, storytelling, and open-ended text generation. Its context window is limited to around 4–6K tokens, and no official benchmark scores have been published. Developers should consider it an experimental community model best fit for creative and conversational use cases rather than production workloads requiring verified performance.

Context Window 6K

tokens

Max Output 1K

tokens

Input Cost $3.75

per million tokens

Output Cost $7.5

per million tokens

Release Date Nov 5, 2023

 

Code Example

Add AI to your app with the Puter.js AI API — no API keys or setup required.

// npm install @heyputer/puter.js
import { puter } from '@heyputer/puter.js';

puter.ai.chat("Explain quantum computing in simple terms").then(response => {
    document.body.innerHTML = response.message.content;
});

<html>
<body>
    <script src="https://js.puter.com/v2/"></script>
    <script>
        puter.ai.chat("Explain quantum computing in simple terms").then(response => {
            document.body.innerHTML = response.message.content;
        });
    </script>
</body>
</html>

Frequently Asked Questions

How do I use Goliath 120B?

You can access Goliath 120B by Alpindale through Puter.js AI API. Include the library in your web app or Node.js project and start making calls with just a few lines of JavaScript — no backend and no configuration required. You can also use it with Python or cURL via Puter's OpenAI-compatible API.

Is Goliath 120B free?

Yes, it is free if you're using it through Puter.js. With the User-Pays Model, you can add Goliath 120B to your app at no cost — your users pay for their own AI usage directly, making it completely free for you as a developer.

What is the pricing for Goliath 120B?
Goliath 120B costs $3.75 per 1M input tokens and $7.5 per 1M output tokens.
Price per 1M tokens
Input$3.75
Output$7.5
Who created Goliath 120B?

Goliath 120B was created by Alpindale and released on Nov 5, 2023.

What is the context window of Goliath 120B?

Goliath 120B supports a context window of 6K tokens. For reference, that is roughly equivalent to 12 pages of text.

What is the max output length of Goliath 120B?

Goliath 120B can generate up to 1K tokens in a single response.

Does it work with React / Vue / Vanilla JS / Node / etc.?

Yes — the Goliath 120B API works with any JavaScript framework, Node.js, or plain HTML through Puter.js. Just include the library and start building. See the documentation for more details.

Get started with Puter.js

Add AI to your application without worrying about API keys or setup.

Explore Models View Tutorials