The most uncensored daily driver — and it's free.
Cognitive Computations × Venice.ai · Mistral Small 24B · 24B parameters · 32K context · Free · Censorship: none
Dolphin Mistral 24B Venice Edition is what the Dolphin project has always been about, taken to its logical end: a capable mid-size model with the corporate guardrails stripped out at training time, not bolted on after. Built on Mistral Small 24B by Cognitive Computations with Venice.ai, it answers direct questions directly — health, legal gray areas, security research, dark fiction — without the apology paragraph first.
It's the default model on OpenRogue for a reason. At 24B parameters it's fast enough for rapid back-and-forth, smart enough for real work, and blunt enough that you stop re-phrasing questions to get past a filter. If you're new to uncensored AI chat, start here — it costs nothing.
Yes — uncensored at the fine-tune level, not just un-prompted. It was trained to comply with the user rather than refuse, so it handles adult, controversial, and edgy topics without moralizing. OpenRogue adds no extra filter on top.
Yes. It's OpenRogue's free default model — 20 messages a day with no credit card. Pro removes the daily cap.
Direct Q&A, blunt feedback, security and research questions other models dodge, and unfiltered creative writing. For maximum prose quality at larger scale, step up to Hermes 3 405B or Magnum v4 72B.
Related models: Hermes 3 70B · Rocinante · Magnum v4