DeepHermes 3 Llama 3.1 8B Preview
DeepHermes 3 Llama 3.1 8B Preview is Nous Research's language model. An 8B-parameter preview of Nous Research's DeepHermes 3, built on Llama 3.1 with hybrid reasoning and instruction-following capabilities.
| Specifications | |
|---|---|
nousresearch-deephermes-3-llama-3-1-8b-preview | |
| Language | |
| Active | |
| Nous Research | |
| Text | |
| Text | |
| 8B | |
Capabilities
Input1/5
Text✓
Image·
Audio·
Video·
PDF·
Output1/5
Text✓
Image·
Audio·
Video·
Embedding·
Capabilities0/13
Reasoning·
Adaptive Reasoning·
Function Calling·
Parallel Function Calling·
Structured Outputs·
Native JSON Schema·
Web Search·
URL Context·
Computer Use·
Code Execution·
File Search·
Prompt Caching·
Assistant Prefill·
Cheapest Instances to Run It
Cloud GPU instances that can host DeepHermes 3 Llama 3.1 8B Preview, ranked by cheapest on-demand price. The model needs about 19 GB of GPU memory at FP16 precision (estimated from its parameter count), so treat the fit as guidance rather than a guarantee.
All clouds
FP16 (full precision)
US Dollar ($)
Instance | Cloud | GPU | VRAM | Price | Cheapest region | |
|---|---|---|---|---|---|---|
| g2-standard-4 |  GCP | nvidia-l4 | 24 GB | $0.705/hr | us-east4 | |
| g6.xlarge |  AWS | L4 | 22 GB | $0.805/hr | us-east-1 | |
| g2-standard-8 | GCP | nvidia-l4 | 24 GB | $0.851/hr | us-east4 | |
Versions
| Version | Released | Context | Input / 1M | Output / 1M | Status |
|---|---|---|---|---|---|
| Hermes 3 8B TEE | — | 16K | $0.150 | $0.600 | Available |
| Hermes 4 405B | 131K | $1.00 | $3.00 | Available | |
| Hermes 4 70B | 131K | $0.130 | $0.400 | Available | |
| DeepHermes 3 Llama 3.1 8B Preview | — | — | — | — | Current |
| DeepHermes 3 Mistral 24B Preview | — | — | — | — | Available |
| Hermes 3 405B | — | 131K | $0.800 | $0.800 | Available |
| Hermes 3 70B | — | 131K | $0.120 | $0.300 | Available |
| Hermes 3 8B | — | 131K | $0.025 | $0.040 | Available |