Hermes 3 Llama 3.2 3B
Hermes 3 Llama 3.2 3B supports general conversation, reasoning and structured responses. It is a Nous post-training release of a Meta base model.
Training and model behavior
The 3B release is a full-parameter fine-tune of Llama 3.2 3B. Nous trained it on H100 GPUs through Lambda's cloud. It preserves the Hermes ChatML conversation format.Hermes 3 Llama 3.2 3B model card
Working with this model
Practical guidance. Use the shipped chat template when migrating a conversation. Compare instruction following and tool syntax on your own prompts. A larger parameter count increases memory requirements but does not guarantee better answers on every task.
Download formats
Nous also publishes GGUF packages for this model. These are deployment formats of the same release.Hermes 3 Llama 3.2 3B GGUF package
Specifications & access
| Detail | Value and conditions |
|---|---|
| Launch date | |
| Access | Downloadable |
| Model identifiers | NousResearch/Hermes-3-Llama-3.2-3B |
| Context window | 131,072 tokens Configured position limit; practical serving limits depend on the runtime. Hermes 3 Llama 3.2 3B configuration |
| Base model | meta-llama/Meta-Llama-3.2-3BHermes 3 Llama 3.2 3B model card |
| Repository license label | llama3Hermes 3 Llama 3.2 3B model card |
Related models
- Hermes 3 Llama 3.1 70B
Nous Research · Hermes 3
An open-weight Hermes assistant derived from Meta's Llama models.
Launch date August 2024Downloadable - Hermes 3 Llama 3.1 405B
Nous Research · Hermes 3
An open-weight Hermes assistant derived from Meta's Llama models.
Launch date Downloadable - Hermes 3 Llama 3.1 8B
Nous Research · Hermes 3
An open-weight Hermes assistant derived from Meta's Llama models.
Launch date August 2024Downloadable