Hermes 4 70B

Uncensored with an actual reasoning gear.

Nous Research · Llama 3.1 70B · 70B parameters · 131K context · Pro $20/mo · Censorship: none

Hermes 4 is Nous Research's answer to a real gap: models that can reason hard without inheriting the refusal reflexes that usually come bundled with reasoning training. Built on Llama 3.1 70B, it supports deliberate step-by-step thinking when you want depth and direct answers when you don't — and its alignment philosophy is explicitly neutral: the user steers, the model follows.

On OpenRogue it pairs naturally with Thinking mode: flip it on for analysis, strategy, math, or code architecture, and Hermes 4 works the problem instead of hedging it. With 131K context it'll hold an entire document set or codebase brief in its head while it does.

What Hermes 4 is best at

Frequently asked questions

Is Hermes 4 70B censored?

No. Nous Research trains the Hermes line with neutral alignment — the model treats you as the authority on what you need. It reasons carefully but doesn't refuse legal adult topics.

Does Hermes 4 support reasoning like o-series models?

Yes — it's a hybrid reasoner. Use OpenRogue's Thinking mode and it produces deliberate multi-step reasoning before answering; in Instant mode it answers directly.

Hermes 4 vs Hermes 3 — which should I pick?

Hermes 4 for analysis, strategy, and anything that benefits from explicit reasoning. Hermes 3 (70B or 405B) for creative writing and roleplay where flow matters more than deliberation.

Related models: Hermes 3 405B · WizardLM-2 · Hermes 3 70B

Start free → · All models · Pricing