Hermes 4 - Llama-3.1 70B (Non-reasoning)

About the Hermes (Nous) family

Nous Research's Hermes fine-tunes of Llama (8B–405B, with toggleable reasoning in Hermes 4/DeepHermes) — community-driven, steerable, minimally-refusing open models.

How this one is configured

This configuration runs in non-reasoning mode (direct answers, faster and cheaper); ~70B parameters.

Who makes it

Nous Research — United States. Not listed as a provider in this directory.

More from Hermes (Nous)

• DeepHermes 3 - Llama-3.1 8B Preview (Non-reasoning)
• DeepHermes 3 - Mistral 24B Preview (Non-reasoning)
• Hermes 3 - Llama-3.1 70B
• Hermes 4 - Llama-3.1 405B (Non-reasoning)
• Hermes 4 - Llama-3.1 405B (Reasoning)
• Hermes 4 - Llama-3.1 70B (Reasoning)