hermes
3B parameters
Commercial OK
Reviewed May 2026

Hermes 3 Llama 3.2 3B

Nous Research's Hermes 3 fine-tune of Llama 3.2 3B. Strong general-instruction following at the 3B tier.

License: Llama Community License·Released Oct 15, 2024·Context: 131,072 tokens

Overview

Nous Research's Hermes 3 fine-tune of Llama 3.2 3B. Strong general-instruction following at the 3B tier.

Family & lineage

How this model relates to others in its lineage. Family members share architecture and training-data roots; parent / children edges record direct distillation or fine-tune relationships.

Parent / base model
Llama 3.2 3B Instruct3B
Edge
Family siblings (hermes-3)

Strengths

  • Strong 3B instruction tuning
  • Apple Silicon edge-friendly

Weaknesses

  • 3B parameter ceiling limits depth

Quantization variants

Each quantization trades model quality for file size and VRAM. Q4_K_M is the most popular starting point.

QuantizationFile sizeVRAM required
Q4_K_M1.8 GB3 GB

Get the model

HuggingFace

Original weights

huggingface.co/NousResearch/Hermes-3-Llama-3.2-3B

Source repository — direct quantization required.

Hardware that runs this

Cards with enough VRAM for at least one quantization of Hermes 3 Llama 3.2 3B.

Compare alternatives

Models worth comparing

Same parameter band, plus what's one tier above and below — so you can decide what actually fits your hardware.

Frequently asked

What's the minimum VRAM to run Hermes 3 Llama 3.2 3B?

3GB of VRAM is enough to run Hermes 3 Llama 3.2 3B at the Q4_K_M quantization (file size 1.8 GB). Higher-quality quantizations need more.

Can I use Hermes 3 Llama 3.2 3B commercially?

Yes — Hermes 3 Llama 3.2 3B ships under the Llama Community License, which permits commercial use. Always read the license text before deployment.

What's the context length of Hermes 3 Llama 3.2 3B?

Hermes 3 Llama 3.2 3B supports a context window of 131,072 tokens (about 131K).

Source: huggingface.co/NousResearch/Hermes-3-Llama-3.2-3B

Reviewed by RunLocalAI Editorial. See our editorial policy for how we research and verify model claims.

Related — keep moving

Before you buy

Verify Hermes 3 Llama 3.2 3B runs on your specific hardware before committing money.