TextMath and reasoning

Hermes

Nous Research fine-tunes on top of Llama, Mistral, Qwen and Seed-OSS. Valued for precise instruction following, function calling and strict JSON output; they refuse less often than the originals; Hermes 4 has a reasoning mode.

Developer
Nous Research, USA
First release
Jun 2023
Latest release
Nov 2025
Sizes
3B – 405B
License
Commercial use with conditionsDepends on the base: Hermes 4 14B and 4.3 36B, OpenHermes and Mistral-based versions: Apache 2.0; Llama 3 versions: Llama Community License; early LLaMA 1 versions: non-commercial only
Russian
Not supported
Ready-made builds
GGUF, AWQ, GPTQ, MLX (Apple)
Running
Available in OllamaAlso runs without a GPU
Industries
Customer support, Software development
Deploy on your server Hugging Face GitHub

What it does

  • Agents that call functions and APIs
  • Data extraction in strict JSON format
  • Assistant with flexible role and tone settings
  • Role-play scenarios and dialogue simulators

Where it is used

IT and automationCustomer supportStaff trainingGames and entertainment

Hardware requirements

LaptopLaptop or regular PC, up to 8 GB of VRAM — smaller versions
fits
1 GPUOne GPU with 16–80 GB — mid-size versions
fits
ClusterServer with several GPUs — flagship versions
fits

Versions

  1. Hermes 4.3 36B
  2. Hermes 4 (14B / 70B / 405B)
  3. DeepHermes 3 Preview
  4. Hermes 3 (Llama 3.1 8B / 70B / 405B)
  5. Hermes 2 Pro
  6. OpenHermes 2.5 Mistral 7B
  7. Nous-Hermes Llama 2
  8. Nous-Hermes 13B (LLaMA)

How to run it

With Ollama — the fastest wayInstall Ollama on your computer or server and find the model in its library by name. Good enough to try the model on your own tasks in one evening.Find it in the Ollama library
On your own serverWeights are downloaded from Hugging Face and served with vLLM (load and API) or llama.cpp (modest hardware). The model then runs in a closed network with no per-request fees.Hugging Face
How much hardware you needCalculate the VRAM for the model size, context length and number of concurrent requests.Open the hardware calculator

I can set this up end to end: pick the model size, deploy it on your server and connect it to your systems. Quantization compresses a model so it takes less video memory and runs on more modest hardware. Answers change slightly, so quality is checked on your own examples.

Frequently asked questions

Can Hermes be used in a commercial project?

With conditions. License: Depends on the base: Hermes 4 14B and 4.3 36B, OpenHermes and Mistral-based versions: Apache 2.0; Llama 3 versions: Llama Community License; early LLaMA 1 versions: non-commercial only. Restrictions vary — region, company revenue, attribution requirements. Have a lawyer check the terms before a commercial launch.

What hardware does Hermes need?

At minimum: Laptop or regular PC, up to 8 GB of VRAM — smaller versions. Some versions also run on an ordinary CPU, without a GPU. You can calculate the exact VRAM for your model size and context in the hardware calculator.

Does Hermes support Russian?

No. The model card lists its languages and Russian is not among them.

Where can I download Hermes and what does it cost?

The Hermes weights are open and free to download. You only pay for the hardware it runs on and for the setup. Source links are at the bottom of this page.

How I deploy it for clients

  1. SelectionI pick the model size for your task and hardware and test it on your examples.
  2. DeploymentI deploy it on your server or in a closed network and provide an API.
  3. Fine-tuningI fine-tune it on your data (LoRA) or connect a knowledge base — whichever is cheaper for the task.
  4. IntegrationI connect it to your CRM, ERP, bot, website or team chat and set up monitoring.

Similar models

TextLlamaMeta · USACommercial use with conditions

The models that started mass open source in AI. A huge ecosystem of fine-tuned versions and tools.

DetailsTextDolphinCognitive Computations (Eric Hartford) · USACommercial use with conditions

Uncensored fine-tunes of Llama, Mistral, Qwen and others that fulfill almost any request. Filtering and moderation are fully on the deployer; do not show it to customers without your own filter.

DetailsTextTuluAi2 · USACommercial use with conditions

Ai2 fine-tunes of Llama with a fully open recipe: data, code and all intermediate stages. Tulu 3 405B is one of the largest openly fine-tuned models; OLMo chat versions use the same recipe.

Details

Source: huggingface.co/NousResearch/Hermes-4.3-36B. Data checked against the model card on 22 Sep 2026. Have a lawyer review the license before commercial launch.