Magnum v4 72B

Claude-quality prose with the brakes cut.

Anthracite · Qwen 2.5 72B · 72B parameters · 32K context · Pro $20/mo · Censorship: none

Magnum v4 is Anthracite's flagship: a 72B fine-tune of Qwen 2.5 trained with one explicit goal — replicate the prose quality of the frontier Claude models, minus the refusals. The result is a model that writes with rhythm and restraint instead of the over-adjectived mush most open models produce, and that commits to a scene instead of fading to black.

It's the heaviest hitter in OpenRogue's creative lineup for fiction, roleplay, and long-form writing where voice matters. Give it a style to imitate and it actually imitates it; give it a dark premise and it follows through.

What Magnum v4 is best at

• Frontier-grade prose: Trained specifically toward Claude-level writing quality.
• Commits to the scene: No fade-to-black, no sudden narrator morality.
• Strong style transfer: Feed it a voice and it holds the register for pages.
• Roleplay depth: Stays in character across long, layered sessions.

Frequently asked questions

What makes Magnum v4 72B different from other uncensored models?

Its training target. Most uncensored tunes optimize for compliance; Magnum optimizes for prose quality — it was distilled toward the writing style of frontier Claude models. You get literary-grade output and zero refusals.

Is Magnum v4 good for roleplay?

It's one of the strongest open RP models available — long-session character consistency, adult themes handled without breaking, and dialogue that doesn't read like a chatbot.

How do I use Magnum v4 72B online?

It's included in OpenRogue Pro — pick it from the model dropdown and chat in your browser. No GPU, no setup, switch models mid-conversation.

Related models: Euryale · Hermes 3 405B · UnslopNemo

Start free → · All models · Pricing