hermes3:3b

Upstream reference: Hermes 3 Llama 3.2 3B

Publisher: Nous Research

Nous Research documents a full-parameter fine-tune of the Llama 3.2 3B foundation model for general assistants, structured outputs and function-call formats.

Publisher-described context, separate from Sigma5C observations and recorded catalog statistics.

Published upstream specifications

Base lineage

Llama 3.2 3B Source

Card format tags

ChatML, function calling and JSON mode Source

Upstream license metadata

Llama-specific terms; card metadata uses llama3 Source

Publisher-described uses

• Text assistants, structured output and application function-call workflows. Source

Reference limitations

• Hermes is the derivative model publisher; Meta is the underlying base-model developer. Function calls require a surrounding executor. Source

A recorded tag and an upstream card association do not verify the deployed checkpoint, quantization, configured context or current hosted availability.

Publisher sources

• Hermes 3 Llama 3.2 3B official documentation — Nous Research. Checked 2026-11-02.

Links

Recorded references do not establish downloadable weights, licensing or current availability.

• Nous Research — official developer/publisher
• Ollama
• Ollama
• Hugging Face
• Nous Research company release index

Where hermes3:3b comes from

Named in 2 observation pages

• 3B-7B local models — all 53 · V1
• Sub-3B local models — all 34 · V1