Hermes 3 70B Instruct
Summary
Hermes 3 70B Instruct is an open-weight language model from Nousresearch, released on 18 Aug 2024. It accepts text and generates text, with a 131K-token context window and up to 16K output tokens per response.
Hermes 3 is a generalist language model with many improvements over [Hermes 2](/models/nousresearch/nous-hermes-2-mistral-7b-dpo), including advanced agentic capabilities, much better roleplaying, reasoning, multi-turn conversation, long context coherence, and improvements across the...
Last verified 19 Nov 2026. Every figure on this page links to its source.
Specifications
| Developer | Nousresearch |
|---|---|
| Release date | 18 Aug 2024 [OpenRouter] |
| Status | Generally available |
| Weights | Open weights [Hugging Face] |
| License | llama3 [Hugging Face] |
| Parameters | 70.6B [Hugging Face] |
| Context window | 131K (131,072 tokens) [OpenRouter] |
| Max output | 16K tokens [OpenRouter] |
| Knowledge cutoff | 31 Dec 2023 [OpenRouter] |
| Input | Text [OpenRouter] |
| Output | Text [OpenRouter] |
| Reasoning mode | No [OpenRouter] |
| Tool calling | No [OpenRouter] |
| Structured output | Yes [OpenRouter] |
| Hugging Face | NousResearch/Hermes-3-Llama-3.1-70B [Hugging Face] |
Hermes 3 70B Instruct API pricing by provider
USD per million tokens. Sorted by input price.
We do not currently track a paid API listing for this model.
Running Hermes 3 70B Instruct locally
Estimated memory, from the parameter count and the architecture in config.json on Hugging Face. Includes about 0.8 GB of runtime overhead.
| Quantization | Weights | Total, 8K context | Total, 32K context |
|---|---|---|---|
| Q4_K_M (4-bit) | 43 GB | 46 GB | 54 GB |
| Q8_0 (8-bit) | 75 GB | 78 GB | 87 GB |
| FP16 / BF16 (16-bit) | 141 GB | 145 GB | 153 GB |
At 4-bit with an 8K conversation, Hermes 3 70B Instruct needs about 46 GB, more than any single consumer graphics card; it needs a unified-memory machine, a multi-GPU setup or a split between graphics card and system RAM. Check your own hardware, or see Best computer for local AI on our sister site AIPCs.
Frequently asked questions
What is the context window of Hermes 3 70B Instruct?
Hermes 3 70B Instruct has a context window of 131,072 tokens (131K) and can generate up to 16,384 tokens in a single response, according to OpenRouter.
Is Hermes 3 70B Instruct open source?
Hermes 3 70B Instruct is an open-weight model: its weights are published on Hugging Face as NousResearch/Hermes-3-Llama-3.1-70B under the llama3 license. Check the license terms before commercial use.
When was Hermes 3 70B Instruct released?
Nousresearch released Hermes 3 70B Instruct on 18 Aug 2024, according to OpenRouter.
How much VRAM does Hermes 3 70B Instruct need?
About 46 GB at 4-bit (Q4_K_M) with an 8K-token conversation, and about 78 GB at 8-bit. That is more than any single consumer graphics card holds. These are estimates from the model's published parameter count and architecture.
Similar models from other labs
Comparable on output type, weights, release date, price and context window. Prices are the lowest listed, USD per million tokens.
| Model | Lab | Released | Context | Input $/1M | Output $/1M | Weights |
|---|---|---|---|---|---|---|
| Llama 3.1 Euryale 70B v2.2 | Sao10k | 28 Aug 2024 | 131K | $0.85 | $0.85 | Open |
| Llama 3.1 Euryale 70B v2.2 | Sao10k | 28 Aug 2024 | 131K | – | – | Open |
| Command R | Cohere | 30 Aug 2024 | 128K | $0.15 | $0.60 | Open |
| Command R+ | Cohere | 30 Aug 2024 | 128K | $2.50 | $10 | Open |
| Llama Guard 3 8B | Meta | 23 Jul 2024 | 131K | $0.48 | $0.03 | Open |
| Llama-3.1-70B-Instruct | Meta | 23 Jul 2024 | 131K | $0.72 | $0.72 | Open |
Change history
- No longer listed on openrouter