Model overview
What this model is for
llama3-groq-tool-use:70b is a 70-billion-parameter model intended for agents and tool-calling workflows. Ollama describes it as part of a series of models from Groq focused on open-source AI capabilities for tool use and function calling. Its listed capability is tool-calling, making it potentially relevant for applications that need a language model to select, structure, or invoke external functions as part of an agent workflow. No modalities beyond text-oriented model use are listed in the supplied material, and no vision, audio, image-generation, or video capability is documented here. The advertised context window is not available in the supplied material, so application-specific context limits should be verified before deployment. Similarly, no inference speed benchmark, input or output pricing, or licensing terms are provided in the supplied material. The model page records an explicit 70B size, but does not provide evaluation results, quality comparisons, hardware requirements, or operational guidance. Developers should therefore treat tool-calling as the primary documented use case and validate schema adherence, latency, and integration behavior in their own environment.