Llama 3.3 70B Euryale v2.3 for Local AI Role-Play and Story Writing


We're thrilled to announce that Private LLM for macOS v1.9.5 now supports the Llama 3.3 70B Euryale v2.3 model by Sao10k, taking your local AI experience for creative role play and storytelling to the next level.

About Llama 3.3 70B Euryale v2.3 Model

Llama 3.3 70B Euryale v2.3 is a fine-tuned version of the Meta Llama-3.3-70B-Instruct model, meticulously optimized for creative role play and storytelling applications. Its focus on contextually rich and imaginative responses makes it a standout choice for immersive narratives.

  • Enhanced Spatial Awareness: Provides vivid and accurate descriptions of settings and actions, perfect for crafting immersive worlds.
  • Refined Creativity: Delivers diverse and imaginative outputs tailored for storytelling and character-driven interactions.
Screenshot of a futuristic cityscape description where humans and AI coexist, created by Llama 3.3 70B Euryale v2.3 for imaginative storytelling.
Screenshot of a futuristic cityscape description where humans and AI coexist, created by Llama 3.3 70B Euryale v2.3 for imaginative storytelling.
Screenshot of an AI-generated poem from the perspective of an ancient tree, demonstrating Llama 3.3 70B Euryale v2.3's artistic writing abilities.
Screenshot of an AI-generated poem from the perspective of an ancient tree, demonstrating Llama 3.3 70B Euryale v2.3's artistic writing abilities.

Use Cases for AI Role-Play and Story Writing

Llama 3.3 70B Euryale v2.3 unlocks endless possibilities for AI-assisted creativity:

  • Novel Writing: Collaborate with the AI to craft detailed plotlines, dialogues, and character arcs.
  • Tabletop RPGs: Act as a virtual dungeon master, generating adaptive narratives and lifelike character interactions.
  • Interactive Storytelling: Create choose-your-own-adventure tales with dynamic storylines that adapt to user choices.
  • Scriptwriting: Develop engaging scripts for plays, films, or podcasts with the AI assisting in dialogue and scene design.
  • Creative Writing Prompts: Generate unique prompts or story starters to inspire and challenge your writing skills.
Screenshot of a mystery plot set in a space colony, showcasing AI-powered creative writing prompts with Llama 3.3 70B Euryale v2.3.
Screenshot of a mystery plot set in a space colony, showcasing AI-powered creative writing prompts with Llama 3.3 70B Euryale v2.3.

Creating Custom Chatbots with Apple Shortcuts

With Private LLM’s deep integration into the Apple ecosystem, you can easily create personalized chatbots using Apple Shortcuts. Define custom system prompts to craft distinct personas for your needs—whether it’s a role-play companion, an assistant, or a fictional character. These chatbots can be activated with a tap or a Siri command, allowing seamless interaction across different workflows. Tailor these personas to suit specific creative or professional use cases, enhancing both productivity and creativity.

Screenshot depicting a dialogue between a medieval knight and a time-traveling scientist, crafted by Llama 3.3 70B Euryale v2.3 for dynamic role-playing scenarios.
Screenshot depicting a dialogue between a medieval knight and a time-traveling scientist, crafted by Llama 3.3 70B Euryale v2.3 for dynamic role-playing scenarios.

Privacy and Private LLM

At Private LLM, your privacy is paramount. All AI processing occurs entirely on your device, ensuring your narratives, ideas, and personal data stay secure. This local AI approach is ideal for creative projects, enabling you to freely explore imaginative scenarios without concerns about data leaks.

System Requirements

To use this model, your system must meet these requirements:

  • Hardware: Minimum of 48 GB RAM.
  • Compatibility: Apple Silicon Macs only.

Ollama vs. Private LLM: Llama 3.3 70B Euryale v2.3

While Ollama and Private LLM both offer local AI solutions, Private LLM stands apart with its OmniQuant quantization technology, which delivers:

  • Faster Performance: OmniQuant ensures quicker response times by preserving weight distribution more effectively than Ollama’s Round-to-Nearest (RTN) method.
  • Higher Model Fidelity: Models quantized with OmniQuant retain better perplexity scores, resulting in more coherent and contextually accurate outputs.

Want to see the difference for yourself? Compare Ollama vs. Private LLM.


Try Llama 3.3 70B Euryale v2.3 in Private LLM

Screenshot showing an AI-generated monologue for role-play using Llama 3.3 70B Euryale v2.3, highlighting immersive storytelling capabilities.
Screenshot showing an AI-generated monologue for role-play using Llama 3.3 70B Euryale v2.3, highlighting immersive storytelling capabilities.

Download Private LLM for macOS v1.9.5, load Llama 3.3 70B Euryale v2.3, and dive into a world of creative storytelling and role play. Whether you're crafting an epic novel, running a tabletop RPG session, or exploring interactive storytelling, this model delivers unparalleled flexibility and creativity—all on your Mac, without subscriptions or data compromises.


Download Private LLM on the App Store
Stay connected with Private LLM! Follow us on X for the latest updates, tips, and news. Want to chat with fellow users, share ideas, or get help? Join our vibrant community on Discord to be part of the conversation.