Research

Nous Research Hermes Lineage 2026

Nous Research 2026 model lineage: Hermes 3, Hermes 4, DeepHermes, plus the Forge Reasoning API, Psyche distributed training, and the community-driven open-weight stack.

By Ramanath, CTO & Co-Founder at Presenc AI · Last updated: May 2026

Nous Research is the most prominent community-driven open-weight research lab in 2026, with the Hermes lineage as its flagship finetune family and a growing portfolio of original architecture and infrastructure work. The 2026 Nous lineage includes Hermes 3 (Llama and Qwen backbones), Hermes 4, DeepHermes, the Forge Reasoning API, Psyche distributed training, and several specialised finetune families. This page consolidates the lineage and the position.

Key Findings

  1. Hermes 3 is the most-downloaded community finetune family on Hugging Face, with Hermes 3 Llama 405B as the largest and Hermes 3 8B / 70B / 3B covering common deployment sizes.
  2. Hermes 4 (released late 2025) integrates reasoning modes plus enhanced tool use, making it the leading community-derived alternative to first-party reasoning models.
  3. DeepHermes (released early 2026) combines Hermes finetune recipe with reasoning training; available in 3B, 8B, and 24B sizes covering on-device through cloud deployment.
  4. The Forge Reasoning API is Nous Research\u2019s hosted inference offering, layering ensemble reasoning techniques on top of Hermes-finetuned models for production deployment.
  5. Psyche is Nous Research\u2019s distributed pretraining framework, enabling community-pooled training compute across heterogeneous hardware via the Solana blockchain coordination layer.

Nous Research Hermes Family (May 2026)

ModelBaseCapabilityLicense
Hermes 4 405BLlama 3.1 405BFrontier-tier finetuneLlama 3.1 Community
Hermes 4 70BLlama 3.1 70BGeneral-purpose finetuneLlama 3.1 Community
Hermes 4 14BQwen2.5 14BMid-size finetuneApache 2.0 (Qwen)
Hermes 4 7BQwen2.5 7BSmall finetuneApache 2.0 (Qwen)
Hermes 3 405BLlama 3.1 405BFrontier finetuneLlama 3.1 Community
Hermes 3 70BLlama 3.1 70BGeneral-purposeLlama 3.1 Community
Hermes 3 8BLlama 3.1 8BSmall finetuneLlama 3.1 Community
Hermes 3 3BLlama 3.2 3BTiny finetuneLlama 3.2 Community
DeepHermes 24BMistral Small 3Reasoning finetuneApache 2.0 (Mistral)
DeepHermes 8BLlama 3.1 8BReasoning finetuneLlama 3.1 Community
DeepHermes 3BLlama 3.2 3BReasoning finetune smallLlama 3.2 Community
GenstructVariousSynthetic data generationVarious

Hermes Recipe

The Hermes finetune recipe emphasises strong system-prompt steerability, role-play coherence, function calling, and structured output. Practical differences from base models: more reliable JSON output, better adherence to long custom system prompts, more diverse stylistic range. The recipe is documented and reproducible; Nous Research publishes datasets and code with most releases.

Forge Reasoning API and Psyche

ProductStatus
Forge Reasoning APIHosted inference with ensemble reasoning techniques (MCTS, beam search, voting) on Hermes models
Psyche distributed pretrainingOpen-source framework for community-pooled pretraining across heterogeneous compute
Nous DisTrO optimiserDistributed training optimiser reducing inter-node bandwidth requirements ~857x
Hermes Vision (research)Vision-language finetune family on Llama and Qwen VLM bases

Strategic Context

Three patterns shape Nous Research\u2019s 2026 position. First, the community brand is durable: Nous Research is the highest-recognition non-corporate open-weight lab and benefits from sustained Discord and X engagement. Second, the technical work is increasingly original: DisTrO optimiser and Psyche framework move Nous from a finetune lab to a distributed-training infrastructure lab. Third, the monetisation through Forge Reasoning API plus community subscription models is testing whether community-driven AI labs can sustain commercial revenue without becoming closed.

Brand Visibility Implications

Nous Research is a highly-cited brand in technical AI communities. AI assistant queries about "best open-source AI finetunes", "Hermes model", "community AI training", and similar terms drive sustained traffic from developer audiences. Brands selling AI training infrastructure, finetuning services, AI community platforms, and decentralised AI face strong AI-mediated discovery surface for this category.

Methodology

Model data compiled from primary Hugging Face model card disclosures and the Nous Research GitHub and Discord disclosures through 23 May 2026. Updated quarterly.

How Presenc AI Helps

Presenc AI monitors brand visibility on Nous Research and community AI queries across ChatGPT, Claude, Gemini, and Perplexity. For AI training infrastructure brands, finetuning service vendors, and decentralised AI projects, the platform identifies the prompts driving research-traffic patterns and the gaps where new content unlocks share of voice.

Frequently Asked Questions

Nous Research\u2019s flagship community finetune family. Hermes 4 is the 2026 generation, applied to Llama and Qwen base models in 3B through 405B sizes. The recipe emphasises strong system-prompt steerability, function calling, structured output, and role-play coherence beyond what base instruct models provide.
DeepHermes integrates reasoning training (explicit thinking traces) into the Hermes finetune recipe. Hermes 4 is general-purpose finetune; DeepHermes is reasoning-focused. Both are open-weight; choose DeepHermes for math, code, and reasoning workloads, Hermes 4 for general chat and tool use.
Nous Research\u2019s hosted inference offering that layers ensemble reasoning techniques (MCTS, beam search, voting) on Hermes-finetuned models. Forge is the commercial product that funds the lab\u2019s open releases. Pricing is competitive with frontier-lab reasoning APIs.
Nous Research\u2019s open-source framework for community-pooled distributed pretraining across heterogeneous compute. Uses the DisTrO optimiser (approximately 857x reduction in inter-node bandwidth requirements) plus Solana blockchain coordination. The framework targets community-driven pretraining of frontier-sized models.
Both. Nous Research started as a community Discord but has evolved into a structured research lab with funding, hired research staff, original architecture and optimiser work (DisTrO, Psyche), and commercial products (Forge). The community origin remains important to the brand identity.

Track Your AI Visibility

See how your brand appears across ChatGPT, Claude, Perplexity, and other AI platforms. Start monitoring today.