GT LLMs

The GT LLM Basic Package showcases a curated collection of AI language models from leading providers, designed to suit different business needs and technical requirements. This package helps organizations access and understand various AI models, from fast, efficient options to more powerful, specialized ones.

Whether you need quick responses, large context windows, or specialized capabilities like coding, these models provide flexibility in how you implement AI solutions. GT Edge excells at providing options across the AI landscape, from Meta’s Llama models and Mistral AI’s Mixtral architecture to specialized tools from Google, Alibaba, and others. Each model is presented with clear specifications and performance characteristics.

Whether you’re looking for fast inference through Groq, specialized model inference through local GPU processing, or anything in-between, GT can run a model to suit your AI needs.

Meta Llama 3/3.1/3.2 Models
Mistral Mixtral 8x7b Models
Alibaba Qwen 2/2.5 Models
Google Gemma/Gemma 2 Models
Microsoft Phi 3 Models
IBM Granite Coder models