---
title: "Nous Research models: release history and timeline"
description: "Open-source AI research company best known for the Hermes series of steerable fine-tuned models and for decentralized training through its Psyche network."
type: "release-archive"
canonical_url: "https://theaiengineering.com/releases/nous-research"
markdown_url: "https://theaiengineering.com/releases/nous-research.md"
author: "The AI Engineering Editors"
publisher: "The AI Engineering"
updated: "2026-11-06"
citation: "The AI Engineering Editors. \"Nous Research models: release history and timeline.\" The AI Engineering, updated Nov 06, 2026. https://theaiengineering.com/releases/nous-research"
license: "CC BY 4.0"
license_url: "https://creativecommons.org/licenses/by/4.0/"
data_csv: "https://theaiengineering.com/releases.csv"
data_json: "https://theaiengineering.com/releases.json"
---

# Nous Research models: release history and timeline

Open-source AI research company best known for the Hermes series of steerable fine-tuned models and for decentralized training through its Psyche network.

- Founded: 2023
- Website: https://nousresearch.com

11 releases from 1 lab, 11 with open weights. Dates are the labs' official announcement dates.

## November 2026

### Arete-27B

Arete-27B is Nous Research's post-trained version of Alibaba's Qwen3.8-27B, which the lab says it fine-tuned to reinforce Western values and reduce refusals, deflections, and state-framed answers on politically sensitive topics.

- Date: 2026-11-06
- Lab: Nous Research
- Type: LLM
- Weights: Open weights
- Modalities: text → text
- Parameters: 27B
- License: Apache-2.0
- Available at launch: Open weights
- Permalink: https://theaiengineering.com/releases/2026/11#arete-27b

Highlights:

- Supervised fine-tuning only, with no reinforcement learning, preference optimization, or architectural changes
- Used Inkling as the teacher and about 52.8 million text-only tokens, trained at 64K context
- Weights, the 803-prompt evaluation, and the training data were published alongside the model

Source: [Introducing Arete-27B: Qwen3.8-27B Post-Trained To Reinforce Western Values | Nous Research](https://nousresearch.com/arete)

## January 2026

### NousCoder-14B

Competitive olympiad programming model from Nous Research, post-trained from Qwen3-14B with reinforcement learning to solve contest-style coding problems and released with open weights under Apache 2.0.

- Date: 2026-01-06
- Lab: Nous Research
- Type: Coding
- Weights: Open weights
- Modalities: text → text
- Parameters: 14B
- License: Apache-2.0
- Available at launch: Open weights
- Permalink: https://theaiengineering.com/releases/2026/01#nouscoder-14b

Highlights:

- Post-trained on Qwen3-14B
- Training context extended from 32K to 40K tokens during RL
- Released under Apache 2.0

Source: [NousCoder-14B: A Competitive Olympiad Programming Model | Nous Research](https://nousresearch.com/nouscoder-14b-a-competitive-olympiad-programming-model)

## December 2025

### Nomos 1

30B open-weights mathematics model released by Nous Research in partnership with Hillclimb, described by Nous as a small but capable mathematician for problem solving.

- Date: 2025-12-09
- Lab: Nous Research
- Type: Reasoning
- Weights: Open weights
- Modalities: text → text
- Parameters: 30B
- License: Apache-2.0
- Available at launch: Open weights
- Permalink: https://theaiengineering.com/releases/2025/12#nomos-1

Highlights:

- Focused on mathematical problem solving
- Built in partnership with Hillclimb
- Published on Hugging Face as nomos-1

Source: [Releases | Nous Research](https://nousresearch.com/releases)

### Hermes 4.3

Update to the Hermes series that nearly matches Hermes 4 70B at half the size, post-trained entirely on Nous Research's decentralized Psyche network.

- Date: 2025-12-03
- Lab: Nous Research
- Type: Reasoning
- Weights: Open weights
- Modalities: text → text
- Context window: 512,000 tokens
- Parameters: 36B
- License: Apache-2.0
- Available at launch: Open weights
- Permalink: https://theaiengineering.com/releases/2025/12#hermes-4-3

Highlights:

- Trained with extended context up to 512K tokens
- Released as Hermes-4.3-Seed-36B
- Psyche-trained version outperformed a centrally trained version on downstream tasks

Source: [Introducing Hermes 4.3: Local Intelligence Globally Trained | Nous Research](https://nousresearch.com/introducing-hermes-4-3)

## August 2025

### Hermes 4

Hybrid-mode reasoning models from Nous Research released with a technical report, led by a frontier model based on Llama 3.1 405B.

- Date: 2025-08-26
- Lab: Nous Research
- Type: Reasoning
- Weights: Open weights
- Modalities: text → text
- Parameters: 14B, 70B and 405B
- License: Llama 3 Community License (70B, 405B); Apache-2.0 (14B)
- Available at launch: Open weights
- Permalink: https://theaiengineering.com/releases/2025/08#hermes-4

Highlights:

- Released as Hermes-4-Llama-3.1-405B, Hermes-4-Llama-3.1-70B and Hermes-4-14B
- 14B model is a small dense variant for local inference
- Hermes 4 Technical Report published the same day

Source: [Releases | Nous Research](https://nousresearch.com/releases)

## February 2025

### DeepHermes-3-Llama-3-8B-Preview

Preview Hermes model from Nous Research that unifies deep reasoning and standard chat modes in a single model, built on Meta's Llama 3 8B.

- Date: 2025-02-14
- Lab: Nous Research
- Type: Reasoning
- Weights: Open weights
- Modalities: text → text
- Parameters: 8B
- License: Llama 3 Community License
- Available at launch: Open weights
- Permalink: https://theaiengineering.com/releases/2025/02#deephermes-3-preview

Highlights:

- Switches between deep reasoning and chat modes
- 3B and Mistral 24B preview versions also released
- Built on Llama 3 8B

Source: [Releases | Nous Research](https://nousresearch.com/releases)

## August 2024

### Hermes 3

Steerable instruction-tuned models created by fine-tuning Llama 3.1 8B, 70B and 405B on primarily synthetic data, with long-term context retention and multi-turn chat.

- Date: 2024-08-15
- Lab: Nous Research
- Type: LLM
- Weights: Open weights
- Modalities: text → text
- Parameters: 8B, 70B and 405B
- License: Llama 3 Community License
- Available at launch: Open weights
- Permalink: https://theaiengineering.com/releases/2024/08#hermes-3

Highlights:

- Released with the Hermes 3 technical report
- Supports complex roleplaying and internal monologue
- A Llama 3.2 3B version followed in December 2024

Source: [Freedom at the Frontier: Hermes 3 | Nous Research](https://nousresearch.com/freedom-at-the-frontier-hermes-3)

## March 2024

### Hermes-2-Pro-Mistral-7B

Hermes 2 Pro model from Nous Research built on Mistral 7B, which Nous describes as a master function-calling model, released under Apache 2.0.

- Date: 2024-03-11
- Lab: Nous Research
- Type: LLM
- Weights: Open weights
- Modalities: text → text
- Parameters: 7B
- License: Apache-2.0
- Available at launch: Open weights
- Permalink: https://theaiengineering.com/releases/2024/03#hermes-2-pro-mistral-7b

Highlights:

- Focused on function calling
- Built on Mistral 7B
- Later followed by Llama 3-based Hermes 2 Pro models

Source: [Releases | Nous Research](https://nousresearch.com/releases)

## January 2024

### Nous-Hermes-2-Mixtral-8x7B

Hermes 2 fine-tune of Mistral AI's Mixtral 8x7B mixture-of-experts model from Nous Research, released in supervised fine-tuned and DPO-trained versions on Hugging Face.

- Date: 2024-01-15
- Lab: Nous Research
- Type: LLM
- Weights: Open weights
- Modalities: text → text
- License: Apache-2.0
- Available at launch: Open weights
- Permalink: https://theaiengineering.com/releases/2024/01#nous-hermes-2-mixtral

Highlights:

- SFT and DPO versions released together
- Quantized GGUF version published the same day
- Built on Mixtral 8x7B

Source: [Releases | Nous Research](https://nousresearch.com/releases)

## December 2023

### Nous-Hermes-2-Yi-34B

Hermes 2 model from Nous Research, a fine-tune of the Yi 34B base model, released openly on Hugging Face under Apache 2.0 in December 2023.

- Date: 2023-12-25
- Lab: Nous Research
- Type: LLM
- Weights: Open weights
- Modalities: text → text
- Parameters: 34B
- License: Apache-2.0
- Available at launch: Open weights
- Permalink: https://theaiengineering.com/releases/2023/12#nous-hermes-2-yi-34b

Highlights:

- Listed by Nous Research as Hermes on Yi
- Built on the Yi 34B base model
- Published under Apache 2.0

Source: [Releases | Nous Research](https://nousresearch.com/releases)

## July 2023

### Nous-Hermes-Llama2-13b

Nous Research's Hermes fine-tune of Meta's Llama 2 13B, an early open-weights entry in the Hermes series of instruction-following models released on Hugging Face.

- Date: 2023-07-21
- Lab: Nous Research
- Type: LLM
- Weights: Open weights
- Modalities: text → text
- Parameters: 13B
- License: MIT
- Available at launch: Open weights
- Permalink: https://theaiengineering.com/releases/2023/07#nous-hermes-llama-2

Highlights:

- Built on Llama 2 13B
- Listed by Nous Research as Hermes on Llama2
- Published on Hugging Face

Source: [Releases | Nous Research](https://nousresearch.com/releases)

## Cite and reuse this data

These release records are free to reuse under CC BY 4.0, including commercially. Credit The AI Engineering and link to this page's URL. Dates are the labs' official announcement dates, and every record links to its source. List fields in the CSV are separated by " | ".

The AI Engineering Editors. "Nous Research models: release history and timeline." The AI Engineering, updated Nov 06, 2026. https://theaiengineering.com/releases/nous-research

HTML link:

```html
<a href="https://theaiengineering.com/releases/nous-research">Nous Research models: release history and timeline</a> (The AI Engineering)
```

- Title: Nous Research models: release history and timeline
- Author: The AI Engineering Editors
- Publisher: The AI Engineering
- Updated: 2026-11-06
- URL: https://theaiengineering.com/releases/nous-research
- Markdown: https://theaiengineering.com/releases/nous-research.md
- License: CC BY 4.0 (https://creativecommons.org/licenses/by/4.0/)
- Full dataset as CSV: https://theaiengineering.com/releases.csv
- Full dataset as JSON: https://theaiengineering.com/releases.json
