Model Library
Nous ResearchReleased August 15, 2024Hermes 3 - Llama-3.1 70B
Nous Research · Released August 15, 2024
Intelligence score
5
At a glance
- Intelligence
- 5
- Speed
- 34.9tokens/sec
- Latency
- 2.17stime to first token
- Input price
- $0.70per 1M tokens
- Output price
- $0.70per 1M tokens
- Context window
- 130Ktokens
- Parameters
- 70.6billions
Summary
Comparison summary
Hermes 3 - Llama-3.1 70B scores 5 (estimated) on the Artificial Analysis Intelligence Index, placing it below average among other open weight non-reasoning models of similar size (median: 7). Hermes 3 - Llama-3.1 70B generates output at 34.9 tokens per second (based on the median across providers serving the model), which is at the lower end compared to other open weight non-reasoning models of similar size (median: 81.5 t/s). Hermes 3 - Llama-3.1 70B costs $0.70 per 1M input tokens (somewhat higher than average, median: $0.53) and $0.70 per 1M output tokens (better than average, median: $1.05), based on the median across providers serving the model.
Specifications
Technical specifications
| Model name | Hermes 3 - Llama-3.1 70B |
|---|---|
| Provider | Nous Research |
| Release date | August 15, 2024 |
| Intelligence score | 5 |
| Speed | 34.9 tokens/sec |
| Latency (TTFT) | 2.17s |
| Input price | $0.70 / 1M tokens |
| Output price | $0.70 / 1M tokens |
| Context window | 130,000 tokens |
| Parameters | 70.6B |
| Reasoning | No |
| Input modalities | text |
| Output modalities | — |
| Open weights | Yes |
| License | LLAMA 3 |
| API availability | — |
| Source | Model Intelligence legacy profile: hermes-3-llama-3-1-70b |
Pricing
Token prices
Price per 1M tokens
Hermes 3 - Llama-3.1 70B, as listed in the catalog record
- Input$0.70
- Output$0.70
| Token type | Price per 1M |
|---|---|
| Input | $0.70 |
| Output | $0.70 |
Model Intelligence legacy profile: hermes-3-llama-3-1-70b
FAQ · 20
Frequently asked questions
Hermes 3 - Llama-3.1 70B was released on August 15, 2024.
Hermes 3 - Llama-3.1 70B was created by Nous Research.
Hermes 3 - Llama-3.1 70B scores 5 (estimated) on the Artificial Analysis Intelligence Index, placing it below average among other open weight non-reasoning models of similar size (median: 7).
Hermes 3 - Llama-3.1 70B generates output at 34.9 tokens per second (based on the median across providers serving the model), which is at the lower end compared to other open weight non-reasoning models of similar size (median: 81.5 t/s).
Hermes 3 - Llama-3.1 70B has a time to first token (TTFT) of 2.17s (based on the median across providers serving the model), which is somewhat higher than average compared to other open weight non-reasoning models of similar size (median: 1.59s).
Hermes 3 - Llama-3.1 70B costs $0.70 per 1M input tokens (somewhat higher than average, median: $0.53) and $0.70 per 1M output tokens (better than average, median: $1.05), based on the median across providers serving the model.
Hermes 3 - Llama-3.1 70B costs $0.70 per 1M input tokens and $0.70 per 1M output tokens (based on the median across providers serving the model). For a blended rate (7:2:1 cache hit/input/output ratio), this is $0.70 per 1M tokens. Pricing may vary by provider.
No, Hermes 3 - Llama-3.1 70B is not a reasoning model. It provides direct responses without extended chain-of-thought reasoning.
Hermes 3 - Llama-3.1 70B supports text only input.
Hermes 3 - Llama-3.1 70B supports text only output.
No, Hermes 3 - Llama-3.1 70B does not support image input. It can only process text.
No, Hermes 3 - Llama-3.1 70B is not multimodal. It only supports text only input.
Hermes 3 - Llama-3.1 70B has a context window of 130k tokens. This determines how much text and conversation history the model can process in a single request.
Yes, Hermes 3 - Llama-3.1 70B is open weights. The model weights are publicly available and can be downloaded for self-hosting.
Hermes 3 - Llama-3.1 70B has 70.6 billion parameters.
Hermes 3 - Llama-3.1 70B is released under the LLAMA 3.1 COMMUNITY LICENSE AGREEMENT license. This license allows commercial use.
Hermes 3 - Llama-3.1 70B achieves a score of 5 on the Artificial Analysis Intelligence Index. This composite benchmark evaluates models across reasoning, knowledge, mathematics, and coding.
Hermes 3 - Llama-3.1 70B has a knowledge cutoff of December 2023. The model's training data includes information up to this date.
Yes, Hermes 3 - Llama-3.1 70B is available via API through 1 provider.
Hermes 3 - Llama-3.1 70B is available through 1 API provider.