DeepHermes 3
by Nous Research · open-source · Last verified 2026-04-24
DeepHermes 3 by Nous Research is a reasoning-augmented open-weight model that combines DeepSeek R1-style chain-of-thought training with Hermes instruction tuning. It supports toggling between standard inference and extended thinking mode, offering one of the first open-source models with controllable reasoning depth for agentic applications.
https://huggingface.co/NousResearch/DeepHermes-3-Llama-3-8B-Preview ↗D
D—Poor
Adoption: C+Quality: B+Freshness: ACitations: FEngagement: F
Specifications
- License
- Open Source
- Pricing
- open-source
- Capabilities
- Integrations
- Use Cases
- API Available
- No
- Modalities
- Tags
- llama, reasoning, chain-of-thought, open-weights, agentic, nous-research
- Added
- 2026-04-24
- Completeness
- 73%
Index Score
34Adoption
50
Quality
70
Freshness
80
Citations
0
Engagement
0