AI Role Play and Story Writing with EVA LLaMA 3.33 70B in Private LLM


We're excited to announce that Private LLM for macOS v1.9.5 now supports the EVA LLaMA 3.33 70B model, enhancing your local AI experience for role play and story writing.

About EVA LLaMA 3.33 70B

EVA LLaMA 3.33 70B is a fine-tuned version of Meta Llama 3.3 70B Instruct model, optimized for AI role play and story writing. Trained on a diverse mix of synthetic and natural data, it delivers versatile and creative outputs, making it ideal for immersive narratives and character interactions.

  • Enhanced Creativity: Generates imaginative and contextually rich responses, elevating your AI role play and story writing experiences.

  • Optimized Performance: Fine-tuned to provide coherent and engaging narratives, ensuring a seamless user experience.

Screenshot showcasing EVA LLaMA 3.33 70B generating an AI role play monologue about discovering superpowers.
Screenshot showcasing EVA LLaMA 3.33 70B generating an AI role play monologue about discovering superpowers.

Use Cases for AI Role Play and Story Writing

EVA LLaMA 3.33 70B opens up a world of possibilities for AI-assisted creativity:

  • Novel Writing: Collaborate with the AI to develop plotlines, create dialogues, and flesh out characters, enhancing your storytelling process.

  • Tabletop RPGs: Generate dynamic narratives and character interactions, acting as a virtual dungeon master to enrich your gaming sessions.

  • Interactive Storytelling: Craft choose-your-own-adventure tales where the AI adapts the storyline based on user choices, providing a personalized experience.

  • Scriptwriting: Develop engaging scripts for plays, movies, or podcasts, with the AI assisting in dialogue creation and scene setting.

  • Creative Writing Exercises: Use the AI to generate prompts, story starters, or writing challenges to inspire and hone your writing skills.

Screenshot of EVA LLaMA 3.33 70B creating an AI role play description of a futuristic city where humans and AI coexist harmoniously
Screenshot of EVA LLaMA 3.33 70B creating an AI role play description of a futuristic city where humans and AI coexist harmoniously
Screenshot of EVA LLaMA 3.33 70B generating a poetic AI story writing perspective from an ancient tree.
Screenshot of EVA LLaMA 3.33 70B generating a poetic AI story writing perspective from an ancient tree.

Creating Custom Chatbots with Apple Shortcuts

With Private LLM's integration into the Apple ecosystem, you can create personalized chatbots for various personas using Apple Shortcuts. Start by setting up a new Shortcut and configuring it to interact with Private LLM. Define system prompts that outline the behavior and characteristics of your custom persona—whether it's a helpful assistant, a fictional character, or a creative role-play companion. Once set up, you can trigger these personas with a simple voice command or tap, making it easy to switch between different chatbots tailored to your needs. This feature allows you to seamlessly integrate custom character interactions into your daily workflows or creative projects.

Privacy and Private LLM

At Private LLM, we prioritize your privacy. All AI processing occurs directly on your device, ensuring that your creative ideas, narratives, and personal data remain confidential. This local AI processing is particularly beneficial for role play and story writing, as it allows you to explore imaginative scenarios without concerns about data security or privacy breaches.

System Requirements

To utilize this model, ensure your system meets the following requirements:

  • Hardware: At least 48 GB of RAM.

  • Compatibility: Apple Silicon Macs only.

Ollama vs. Private LLM

While both Private LLM and Ollama offer local AI solutions, Private LLM utilizes OmniQuant for quantization, preserving the model's weight distribution more effectively than the traditional Round-to-Nearest (RTN) quantization employed by Ollama. This results in:

  • Better Inference Performance: Models quantized with OmniQuant run faster, providing quicker responses without compromising accuracy.

  • Improved Model Perplexity: OmniQuant maintains higher model fidelity, leading to more coherent and contextually accurate text generation.

Don’t just take our word for it—compare for yourself.


Try EVA LLaMA 3.33 70B in Private LLM

Screenshot of EVA LLaMA 3.33 70B generating a detailed AI story writing outline for a space colony mystery.
Screenshot of EVA LLaMA 3.33 70B generating a detailed AI story writing outline for a space colony mystery.
Screenshot showcasing EVA LLaMA 3.33 70B generating an AI role play dialogue between a medieval knight and a time-traveling scientist.
Screenshot showcasing EVA LLaMA 3.33 70B generating an AI role play dialogue between a medieval knight and a time-traveling scientist.

Download Private LLM for macOS v1.9.5, load EVA LLaMA 3.33 70B, and dive into a world of AI role play and story writing. Whether you’re writing a novel, running a tabletop RPG session, or just experimenting with narrative ideas, EVA LLaMA 3.33 70B offers a flexible local AI solution right on your Mac—no subscription required.


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.