Nous Hermes 2 8B
by Nous Research · nous-hermes family
8B
parameters
text-generation code-generation reasoning creative-writing
Nous Hermes 2 8B is the compact variant from Nous Research's instruction-tuned model series. It provides solid general-purpose performance in text generation, code generation, and reasoning tasks while remaining accessible on consumer hardware. As the smaller sibling of the 34B model, Nous Hermes 2 8B is ideal for users with limited VRAM who still want a capable instruction-following model for everyday tasks and creative writing.
Quick Start with Ollama
ollama run 8b-q4_K_M Resources
Ollama
| Creator | Nous Research |
| Parameters | 8B |
| Architecture | transformer-decoder |
| Context | 8K tokens |
| Released | Mar 10, 2024 |
| License | Apache 2.0 |
| Ollama | nous-hermes2:8b |
Quantization Options
| Format | File Size | VRAM Required | Quality | Ollama Tag |
|---|---|---|---|---|
| Q4_K_M rec | 4 GB | 6 GB | | 8b-q4_K_M |
| Q8_0 | 8 GB | 10 GB | | 8b-q8_0 |
| F16 | 16 GB | 18 GB | | 8b-fp16 |
Compatible Hardware
Q4_K_M requires 6 GB VRAM
Benchmark Scores
62.0
mmlu