Nous Research

Models & tools

• Hermes 4 405B

  Nous Research · Hermes 4

  A Llama 3.1 405B derivative with optional reasoning and structured output.

  Launch date 26 August 2025Downloadable
• 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 15 August 2024Downloadable
• Arete 27B

  Nous Research · Arete

  A Qwen derivative trained to change responses on political and social topics.

  Launch date 6 November 2026Downloadable
• NousCoder 14B

  Nous Research · NousCoder

  A Qwen3 derivative trained for competitive programming.

  Launch date 6 January 2026Downloadable
• Nomos 1

  Nous Research · Nomos

  A mathematical reasoning model developed with Hillclimb AI.

  Launch date 9 December 2025Downloadable
• Hermes 4.3 36B

  Nous Research · Hermes 4

  A Seed-OSS derivative post-trained across the Psyche network.

  Launch date 3 December 2025Downloadable
• Hermes 4.3 36B Centralized

  Nous Research · Hermes 4

  A separately trained control model for the Hermes 4.3 research.

  Launch date 3 December 2025Research releaseDownloadable
• Hermes 4 14B

  Nous Research · Hermes 4

  A Qwen3-14B derivative with optional reasoning and structured output.

  Launch date September 2025Downloadable
• Hermes 4 70B

  Nous Research · Hermes 4

  A Llama 3.1 70B derivative with optional reasoning and structured output.

  Launch date 26 August 2025Downloadable
• DeepHermes Ascension Maze

  Nous Research · Atropos experiments

  An experimental DeepHermes reinforcement-learning artifact.

  Launch date April 2025Research releaseDownloadable
• DeepHermes Egregore v1

  Nous Research · Atropos experiments

  An experimental DeepHermes reinforcement-learning artifact.

  Launch date April 2025Research releaseDownloadable
• DeepHermes Egregore v2

  Nous Research · Atropos experiments

  An experimental DeepHermes reinforcement-learning artifact.

  Launch date April 2025Research releaseDownloadable
• DeepHermes Financial Fundamentals Prediction Specialist

  Nous Research · Atropos experiments

  A research model for predicting the direction of company financial metrics.

  Launch date April 2025Research releaseDownloadable
• DeepHermes Tool Calling Specialist

  Nous Research · Atropos experiments

  An experimental model trained to improve tool calls during reasoning.

  Launch date April 2025Research releaseDownloadable
• Minos v1

  Nous Research · Minos

  A classifier for refusals in assistant responses.

  Launch date April 2025Downloadable
• DeepHermes 3 Llama 3B Preview

  Nous Research · DeepHermes

  A preview model with direct-answer and extended-reasoning modes.

  Launch date 13 March 2025PreviewDownloadable
• DeepHermes 3 Mistral 24B Preview

  Nous Research · DeepHermes

  A preview model with direct-answer and extended-reasoning modes.

  Launch date 13 March 2025PreviewDownloadable
• DeepHermes 3 Llama 8B Preview

  Nous Research · DeepHermes

  A preview model with direct-answer and extended-reasoning modes.

  Launch date February 2025PreviewDownloadable
• Hermes 3 Llama 3.2 3B

  Nous Research · Hermes 3

  An open-weight Hermes assistant derived from Meta's Llama models.

  Launch date 11 December 2024Downloadable
• 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
• Hermes 2 Pro Llama 3 70B

  Nous Research · Hermes 2 Pro

  A Hermes release trained for function calls and JSON responses.

  Launch date 27 June 2024Downloadable
• Hermes 2 Theta Llama 3 70B

  Nous Research · Hermes 2 Theta

  A merged model with additional preference training.

  Launch date 20 June 2024Research releaseDownloadable
• Hermes 2 Theta Llama 3 8B

  Nous Research · Hermes 2 Theta

  A merged model with additional preference training.

  Launch date May 2024Research releaseDownloadable
• Hermes 2 Pro Mistral 7B

  Nous Research · Hermes 2 Pro

  A Hermes release trained for function calls and JSON responses.

  Launch date 11 March 2024Downloadable
• Genstruct 7B

  Nous Research · Genstruct

  A model that generates instruction data from source text.

  Launch date 7 March 2024Downloadable
• OLMo Bitnet 1B

  Nous Research · OLMo Bitnet

  A research model that explores low-bit training.

  Launch date March 2024Research releaseDownloadable
• Nous Hermes 2 Mistral 7B DPO

  Nous Research · Hermes 2

  An earlier instruction-tuned Hermes model with downloadable weights.

  Launch date 20 February 2024Downloadable
• Nous Hermes 2 Mixtral 8x7B DPO

  Nous Research · Hermes 2

  Mixtral 8x7B instruction model with a further direct preference optimization stage.

  Launch date 15 January 2024Downloadable
• Nous Hermes 2 Mixtral 8x7B SFT

  Nous Research · Hermes 2

  Supervised instruction tuning of Mixtral 8x7B, with ChatML conversation formatting.

  Launch date 15 January 2024Downloadable
• Hermes 2 Pro Llama 3 8B

  Nous Research · Hermes 2 Pro

  A Hermes release trained for function calls and JSON responses.

  Launch date 2024Downloadable
• Nous Hermes 2 SOLAR 10.7B

  Nous Research · Hermes 2

  An earlier instruction-tuned Hermes model with downloadable weights.

  Launch date January 2024Downloadable
• YaRN SOLAR 10.7B 32K

  Nous Research · YaRN

  A SOLAR base model extended through long-context training.

  Launch date January 2024Research releaseDownloadable
• YaRN SOLAR 10.7B 64K

  Nous Research · YaRN

  A SOLAR base model extended through long-context training.

  Launch date January 2024Research releaseDownloadable
• Nous Hermes 2 Yi 34B

  Nous Research · Hermes 2

  An earlier instruction-tuned Hermes model with downloadable weights.

  Launch date 25 December 2023Downloadable
• YaRN Mistral 7B 128K

  Nous Research · YaRN

  A continued-pretraining model for longer Mistral sequences.

  Launch date 2 November 2023Research releaseDownloadable
• Nous Capybara 34B

  Nous Research · Capybara

  A conversation model trained with Nous's synthetic-data method.

  Launch date November 2023Downloadable
• Obsidian 3B v0.5

  Nous Research · Obsidian

  A compact vision-language research release.

  Launch date 30 October 2023PreviewDownloadable
• Nous Capybara 3B v1.9

  Nous Research · Capybara

  A conversation model trained with Nous's synthetic-data method.

  Launch date October 2023Downloadable
• OpenHermes 2 Mistral 7B

  Nous Research · OpenHermes

  A Mistral instruction model published by Teknium.

  Launch date October 2023Downloadable
• Nous Capybara 7B v1

  Nous Research · Capybara

  A conversation model trained with Nous's synthetic-data method.

  Launch date September 2023Downloadable
• Nous Hermes Llama 2 70B

  Nous Research · Nous Hermes

  An original-dataset Hermes fine-tune of Llama 2.

  Launch date August 2023Downloadable
• Nous Hermes Llama 2 13B

  Nous Research · Nous Hermes

  An original-dataset Hermes fine-tune of Llama 2.

  Launch date 21 July 2023Downloadable
• Nous Hermes Llama 2 7B

  Nous Research · Nous Hermes

  An original-dataset Hermes fine-tune of Llama 2.

  Launch date July 2023Downloadable
• Redmond Puffin 13B

  Nous Research · Puffin

  A Llama 2 fine-tune focused on extended conversations.

  Launch date July 2023Downloadable
• Nous Hermes 13B

  Nous Research · Nous Hermes

  The first-generation Hermes instruction model on Llama 13B.

  Launch date June 2023Downloadable
• GPT4 x Vicuna 13B

  Nous Research · Early Nous instruction models

  An early instruction fine-tune of Vicuna 13B.

  Launch date 2023Downloadable
• Nous Capybara 7B v1.9

  Nous Research · Capybara

  A conversation model trained with Nous's synthetic-data method.

  Launch date 2023Downloadable
• Nous Hermes 2 Vision Alpha

  Nous Research · Hermes Vision

  An early vision-language model with function-call training.

  Launch date 2023PreviewDownloadable
• Nous Puffin 70B

  Nous Research · Puffin

  A Llama 2 fine-tune focused on extended conversations.

  Launch date 2023Downloadable
• OpenHermes 13B

  Nous Research · OpenHermes

  A Teknium instruction model trained on a public Hermes dataset.

  Launch date 2023Downloadable
• OpenHermes 2.5 Mistral 7B

  Nous Research · OpenHermes

  A coding-enriched continuation of OpenHermes 2.

  Launch date 2023Downloadable
• OpenHermes 7B

  Nous Research · OpenHermes

  A Teknium instruction model trained on a public Hermes dataset.

  Launch date 2023Downloadable
• Redmond Hermes Coder 15B

  Nous Research · Redmond Hermes

  An experimental instruction fine-tune of WizardCoder.

  Launch date 2023Research releaseDownloadable
• YaRN Llama 2 13B 128K

  Nous Research · YaRN

  A Llama 2 model with continued training for longer context.

  Launch date 2023Research releaseDownloadable
• YaRN Llama 2 13B 64K

  Nous Research · YaRN

  A Llama 2 model with continued training for longer context.

  Launch date 2023Research releaseDownloadable
• YaRN Llama 2 70B 32K

  Nous Research · YaRN

  A long-context research extension of Llama 2 70B.

  Launch date 2023Research releaseDownloadable
• YaRN Llama 2 7B 128K

  Nous Research · YaRN

  A Llama 2 model with continued training for longer context.

  Launch date 2023Research releaseDownloadable
• YaRN Llama 2 7B 64K

  Nous Research · YaRN

  A Llama 2 model with continued training for longer context.

  Launch date 2023Research releaseDownloadable
• YaRN Mistral 7B 64K

  Nous Research · YaRN

  A continued-pretraining model for longer Mistral sequences.

  Launch date 2023Research releaseDownloadable
• Nous Hermes 2 Llama 2 70B

  Nous Research · Hermes 2

  An earlier instruction-tuned Hermes model with downloadable weights.

  Launch date not confirmedDownloadable