DS Archive: L3.3 70B Magnum v4 SE

This model is no longer available.

Add AI to your application with Puter.js.

Explore Other Models

Model Card

L3.3 70B Magnum v4 SE is a creative writing and roleplay fine-tune of Meta's Llama 3.3 70B Instruct, made by Doctor-Shotgun as part of the Magnum model line associated with the Anthracite community.

It is trained as an rsLoRA adapter on a revised version of the Magnum v4 dataset with some elements of the earlier v2 data reintroduced, after the creator found the preceding 72B Magnum release unsatisfying. The aim is to emulate the prose style of Claude 3 Sonnet and Opus on a 70B base.

The model follows the Llama 3 chat template and treats all output as fiction rather than factual content. The creator recommends prefill for roleplay use and notes that "Claude-isms" can appear in outputs, a byproduct of the training objective.

It suits developers who want open-weight, Llama-3.3-based prose generation for storytelling and character dialogue applications.

Context Window 32K

tokens

Max Output 32K

tokens

Input Cost $0

per million tokens

Output Cost $0

per million tokens

Release Date N/A

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 L3.3 70B Magnum v4 SE?

L3.3 70B Magnum v4 SE is no longer available through Puter.js. Explore other AI models for alternatives.

What is the pricing for L3.3 70B Magnum v4 SE?

L3.3 70B Magnum v4 SE costs $0 per 1M input tokens and $0 per 1M output tokens.

	Price per 1M tokens
Input	$0
Output	$0

What is the context window of L3.3 70B Magnum v4 SE?

L3.3 70B Magnum v4 SE supports a context window of 32K tokens. For reference, that is roughly equivalent to 64 pages of text.

What is the max output length of L3.3 70B Magnum v4 SE?

L3.3 70B Magnum v4 SE can generate up to 32K tokens in a single response.

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

Yes — the L3.3 70B Magnum v4 SE 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