AI Models
AI Models are the brains behind your conversations on SpicyChat. They determine how a character thinks, responds, and interacts with you. Each model has its own strengths, traits, memory, and level of creativity and precision.
Some AI models may be better at storytelling, while others excel at answering questions or remembering details. By choosing a specific model, you're deciding how your chat will feel, giving you the freedom to tailor your experience on base level to what you want to roleplay, create, and get out of your overall SpicyChat experience.
How Do I Change AI Models?
You can change which AI model you are using for a conversation at any time.
Select the three dots at the top right hand corner of the conversation.
Choose “Generation Settings” in the list of options.
Navigate to the “Inference Model” section.
Select “Change Model.”
Choose the AI Model you wish to use.
Some AI models are only available if you are a Get A Taste, True Supporter or I’m All In subscriber.
What Is Context Memory?
Context Memory is the amount of information the AI will process each time to generate a response, including a characters personality, memories, and your user persona. Your previous chats are then processed with the remaining space.
This helps your character keep track of what’s happening in your conversation, allowing them to remember what you talked about earlier in your chat and generate a coherent response.
The more memory an AI model has, the further back the character you are chatting with can remember, leading to more natural, immersive, and life-like conversations.
What Are AI Model Parameters?
Parameters are like little dails inside the AI model. During training, the AI reads a large amount of text and adjusts the dials to learn how words and ideas fit together.
Each AI model has a set amount of parameters, for example, a 12B model has 12 billion parameters. The more parameters a model has, the more complex concepts it can learn, which leads to more nuanced or intelligent responses.
While larger models can often generate more sophisticated or complicated messages, they also require more computing power, which means they may take longer to generate a response than a model with a smaller number of parameters.
What AI Models Does SpicyChat Offer?
SpicyChat offers a wide range of AI models for you to choose from, each with their own strengths, context memory, and size. Each model offers a unique experience for you to enjoy when chatting with characters.
Context memory is limited by the package you are subscribed to.
SpicyChat Default • 8B • 16K
Our default AI model is optimised for a wide range of use cases, it is flexible and able to be used for multiple types of roleplaying experiences.
The SpicyChat Default model is available to all SpicyChat users.
TheSpice • 8B • 16K
A well performing model based on Llama 3 that generates shorter responses than the default SpicyChat model.
TheSpice is available to all users.
Stheno • 8B • 8K
Stheno is a versatile model, great at crafting immersive stories with well-developed characters and engaging plots. It handles both SFW and NSFW content in a balanced way, allowing for natural build-up without being overly explicit. Perfect for roleplays that need emotional depth, multi-turn coherence, and strong instruction following. Stheno is only available to Get A Taste, True Supporter, and I’m All In subscribers.
Lyra 12B V4 • 12B • 16K
Lyra 12B V4 is designed for rich storytelling and works well with longer conversations. It follows instructions closely and supports multiple languages, including English, French, German, Spanish, Italian, Portuguese, Chinese, Japanese, Korean, Arabic, and Hindi. Perfect for users looking to create detailed roleplays in their preferred language.
Stheno is only available to True Supporter and I’m All In subscribers.
Magnum 12B • 12B • 16K
Magnum 12B is ideal for creating detailed, immersive worlds with rich history and lore. It excels at world-building and setting up complex environments, perfect for roleplays that require deep, informative descriptions. This multilingual model supports multiple languages, providing a wide range of creative possibilities.
Magnum 12B is only available to Get A Taste, True Supporter, and I’m All In subscribers.
DarkForest V3 • 20B • 4K - 8K
DarkForest V3 is designed for mature, complex storytelling. It excels at handling multiple characters in a single scene, following detailed instructions, and seamlessly switching between SFW and NSFW content. With a sharp sense of humor and the ability to explore deep themes, this model is perfect for users seeking sophisticated, creative roleplays.
DarkForest V3 is only available to I’m All In subscribers.
Shimizu 24B • 24B • 16K
This model excels at crafting rich, meaningful storylines and deep character development, particularly for single character roleplays. It transitions smoothly between SFW and NSFW content while driving the plot forward and introducing unexpected, engaging moments. It should also perform decently in French, German, Spanish, Russian, Chinese, Korean and Japanese.
Shimizu 24B is only available to True Supporter and I’m All In subscribers.
Mixtral 8x7B • 45B • 16K
Mixtral 8x7B is great for creating rich, SFW stories with deep and thoughtful plots. It outperforms Llama2 70B in multiple benchmarks, making it one of the top open models. It works well in English, French, Italian, German, and Spanish, and is perfect for writing character driven stories that need careful and expressive details.
Mixtral 8x7B is only available to True Supporter and I’m All In subscribers.
Noromaid 45B • 8B • 16K
Noromaid 45B is designed for detailed, accurate roleplaying, excelling at following instructions and generating realistic, uncensored content. It’s perfect for scenarios that require precision and attention to detail, while still being engaging and immersive.
Norormaid 45B is only available to True Supporter and I’m All In subscribers.
Euryale 70b • 70B • 16K
Euryale is a versatile model, much like Stheno, with increased prompt adherence, awareness of context, and a creative streak that balances well with roleplays of all kinds. It excels in various fields of storytelling whilst displaying dynamic responses that keep engagement.
Euryale 70B is only available to I’m All In subscribers.
Midnight Rose 70b • 70B • 4K
Midnight Rose 70B is specifically designed for immersive roleplaying and storytelling, delivering long, detailed responses that enhance NSFW scenarios. It excels at creating emotionally rich interactions, with complex characters and vivid, atmospheric settings, making it ideal for deep and engaging roleplays.
Midnight Rose 70B is only available to I’m All In subscribers.
Magnum 72B • 72B • 8K
A strong multilingual model designed to replicate the prose quality of the Claude 3 models, specifically Sonnet and Opus. It is based on Qwen2-72B, which demonstrated competitiveness against proprietary models across a series of benchmarks targeting for language understanding, language generation, multilingual capability, coding, mathematics, reasoning and more.
Midnight Rose 70B is only available to I’m All In subscribers.
WizardLM-2 8X22B • 141B • 16K
WizardLM-2 8x22B is a powerful model with advanced reasoning capabilities, making roleplays feel natural and human-like. It excels at handling complex scenarios, multi-turn conversations, and generating thoughtful, coherent responses. Ideal for users who want engaging and intelligent interactions that adapt well to different roleplaying settings.
WizardLM-2 8x22B is only available to I’m All In subscribers.
SpicyXL 132B • 132B • 16K
One of our most advanced models, particularly good for building tension and handling multiple characters in a scene. Our subscribers are raving about this model.
SpicyXL is only available to I’m All In subscribers.
DeepSeek V3 • 671B • 8K
DeepSeek V3 is a boundary-pushing model offering deeper immersion, bolder choices, and characters that truly come alive. It delivers laughter, meticulous detail, and memorable conversations, making it a favourite for creative, unpredictable, and deeply engaging storytelling. Expect a slower response time.
DeepSeek V3 is only available to I’m All In subscribers.
Last updated
Was this helpful?