Euryale 70B v2.1 is a model focused on creative roleplay. It has improved prompt adherence and spatial awareness, and adapts quickly to custom roleplay and formatting.

The Meta Llama 3.3 multilingual large language model (LLM) is an instruction tuned generative model in 70B (text in/text out). It is optimized for multilingual dialogue use cases and outperforms many of the available open source and closed chat models on common industry benchmarks. Llama 3.3 is an auto-regressive language model that uses an optimized transformer architecture. The tuned versions use supervised fine-tuning (SFT) and reinforcement learning with human feedback (RLHF) to align with human preferences for helpfulness and safety.

The Llama 4 collection of models are natively multimodal AI models that enable text and multimodal experiences. These models leverage a mixture-of-experts architecture to offer industry-leading performance in text and image understanding. These Llama 4 models mark the beginning of a new era for the Llama ecosystem. Launching alongside the rest of the Llama 4 series, Llama 4 Maverick is a 17 billion parameter model with 128 experts. Massive MoE with the equivalent of 400B parameters, and a greatly expanded context window.

The Llama 4 collection of models are natively multimodal AI models that enable text and multimodal experiences. These models leverage a mixture-of-experts architecture to offer industry-leading performance in text and image understanding. These Llama 4 models mark the beginning of a new era for the Llama ecosystem. Launching alongside the rest of the Llama 4 series, Llama 4 Scout is a 17 billion parameter model with 16 experts. Fast MoE with the equivalent of 109B parameters, and a greatly expanded context window.

Llama 3.1 is a group of open-source instruction-tuned models from Meta. These multilingual models have a context length of 128K, state-of-the-art tool use, and strong reasoning capabilities. The 8B variant is a light-weight, ultra-fast model that can run anywhere.

Llama 3.2 3B is a 3-billion-parameter multilingual large language model, optimized for advanced natural language processing tasks like dialogue generation, reasoning, and summarization. Designed with the latest transformer architecture, it supports eight languages, including English, Spanish, and Hindi, and is adaptable for additional languages.