MythoMax L2 13B

MythoMax L2 13B is an advanced large language model developed by Gryphe, designed specifically for creative text generation, with a focus on storytelling and role-playing applications. It builds upon the Llama 2 architecture and utilizes a unique tensor merging technique that combines strengths from the MythoLogic-L2 and Huginn models. This enhances its ability to produce coherent, contextually relevant text for extended narratives and complex character interactions. The model features a substantial parameter count of 13 billion, supporting high-quality, fluent text generation. It is configured for optimal use with Alpaca-style prompt formatting and offers multiple quantized versions to suit different hardware configurations. The model can manage extensive context lengths, making it ideal for interactive storytelling, roleplaying games, and more. However, it requires substantial computational resources and careful prompt engineering to function effectively. Potential biases or inaccuracies are a consideration, as with any large language model.

MythoMax L2 13B is a community-developed large language model created by the researcher known as Gryphe, based on Meta's Llama 2 13B architecture. The model is produced through a tensor merging technique that combines the weights of two community models—MythoLogic-L2 (optimized for narrative coherence and creative fiction) and Huginn (a Llama 2-based creative model)—into a single model designed to synthesize the strengths of both. The merging approach does not involve additional training data; it combines pretrained weights directly. The model has approximately 13 billion parameters and uses a 4,096-token context window.

MythoMax L2 13B is optimized for long-form creative text generation, interactive roleplay, and character-based storytelling rather than factual question answering or coding. It uses Alpaca-style prompt formatting and is not instruction-tuned for factual or structured tasks. The model does not support tool use, structured output, or vision. Its performance is primarily evaluated through community qualitative feedback rather than standardized benchmarks.

MythoMax L2 13B is available on Together AI, Fireworks AI, OpenRouter, and Novita AI under an Apache 2.0-compatible community license. It is primarily appropriate for creative writing and roleplay applications where stylistic quality matters more than factual accuracy or structured task completion. For production reasoning, coding, or factual tasks, models with formal instruction tuning and benchmark validation are more appropriate.

MythoMax L2 13B has a 4k-token context window.

MythoMax L2 13B input tokens at $0.06/1M, output at $0.06/1M.