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. As of 17 Oct 2026, the lowest listed API price is $0.70 per million input tokens and $0.70 per million output tokens (OpenRouter), across 1 provider we track.
Open Llama instruction model for multilingual chat, reasoning, and coding
Last verified 17 Oct 2026. Every figure on this page links to its source.
Specifications
| Developer | Nousresearch |
|---|---|
| Release date | 18 Aug 2024 [models.dev] |
| Status | Generally available [models.dev] |
| Weights | Open weights [Hugging Face] |
| License | llama3 [Hugging Face] |
| Parameters | 70.6B [Hugging Face] |
| Context window | 131K (131,072 tokens) [models.dev] |
| Max output | 16K tokens [models.dev] |
| Knowledge cutoff | 31 Dec 2023 [models.dev] |
| Input | Text [models.dev] |
| Output | Text [models.dev] |
| Reasoning mode | No [models.dev] |
| Tool calling | No [models.dev] |
| Structured output | Yes [models.dev] |
| 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.
| Provider | Input | Output | Cached input | Context | Source |
|---|---|---|---|---|---|
| OpenRouter nousresearch/hermes-3-llama-3.1-70b | $0.70 | $0.70 | – | 131K | OpenRouter, 17 Oct 2026 |
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.
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 models.dev.
How much does the Hermes 3 70B Instruct API cost?
Hermes 3 70B Instruct is listed from $0.70 per million input tokens and $0.70 per million output tokens (OpenRouter). Prices last verified 17 Oct 2026.
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 models.dev.
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.
Change history
- License changed from none to llama3
- Parameter count changed from none to 70.6B
- Now listed on OpenRouter
- Added to the directory