Skip to main contentThe Local Bench

Tool use and agents · Nous Research

Hermes 3 8B

Hugging Face: NousResearch/Hermes-3-Llama-3.1-8B · checked 2026-10-13

General assistant with a documented tool-call format.

Datasheet

Maker
Nous Research
Parameters
8.03 BVerifiedsafetensors.total from the HF API Source
Licence
Llama 3 CommunityVerified
Access
Public download
Task (HF pipeline)
text-generation
First published on HF
2024-07-28
Last updated on HF
2024-09-08
Weights in memory
16 GB at 16-bit · 4.9 GB at ~4.85 bitsEstimateParameters × bits ÷ 8. Excludes context cache and runtime overhead; not every model has a 4-bit build.

Benchmark

Not yet measured
BFCL V4, overall accuracy

No comparable public score for this benchmark yet. We will not estimate one.

The description summarises the model card at https://huggingface.co/NousResearch/Hermes-3-Llama-3.1-8B. Parameters and licence are read from the Hugging Face API; the weights-in-memory line is our arithmetic, not a measurement.