← Catalog
DeepHermes 3 Llama 3 8B
AvailableNous ResearchOpen weights
Nous reasoning-oriented Hermes model trained to combine concise answers with optional deep reasoning traces.
Specifications
- License
- Open weights · Llama 3 Community License
- Weights
- Downloadable
- Architecture
- Dense
- Parameters
- 8B
- Context window
- 8K tokens
- Max output
- —
- Knowledge cutoff
- —
- Price (in / out, $/M)
- —
- Modalities
- TextCode
Benchmarks
No benchmark scores recorded yet. Spotted some? Submit a correction.
Vendor-reported figures are claims until independently verified. See methodology.