Hermes 3 70B is an LLM that excels in advanced agentic capabilities, improved roleplaying, reasoning, multi-turn conversations, and long context coherence. It is a finetune of the Llama-3.1 70B model, focusing on user alignment with powerful steering and control capabilities. The model is particularly adept at function calling, structured output generation, and code generation, making it a strong choice for technical tasks. Hermes 3 70B is competitive with Llama-3.1 Instruct models and is compatible with OpenAI endpoints.

Metric	Value
Parameter Count	70 billion
Mixture of Experts	No
Context Length	Unknown
Multilingual	Unknown
Quantized*	Unknown

*Quantization is specific to the inference provider and the model may be offered with different quantization levels by other providers.