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.
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.
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 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