Nous Llama 3 Models by Nous Research
Last refreshed 2026-05-19. Next refresh: weekly.
Details
About
The Nous Llama 3 large language model (LLM) family is crafted from Meta's Llama 3 architecture and fine-tuned by Nous Research. It includes models of varying sizes, such as the 8B, 70B, and an impressive 405B parameter model named Hermes 3. Hermes 3 is particularly notable for its superior reasoning abilities and adeptness in following instructions. The 8B parameter model, accessible on Hugging Face, excels in dialogue, outperforming many open-source chat models on traditional benchmarks. The Nous Llama 3 models cater to diverse applications, ranging from sophisticated chatbots and AI writing assistants to advanced AI agents, and are conveniently available on platforms like Ollama and Hugging Face 35.
Decision facts
- Best fit
- agent workflowschatbot and role-playing use cases
- Capability starting point
- Nous Llama 3 70B with 8k context
- Lowest tracked input
- Nous Llama 3 8B · $0.37/1M · Microsoft Foundry
- Closest related family
- Hermes 2
Current Variants
Use-when guidance is based on each model's tracked capabilities, context window, release date, and replacement status.
Use when the workload needs 8k context and 70B parameters.
Use when the workload needs 8k context and 8B parameters.
| Model | Use when | Released | Signals | Status |
|---|---|---|---|---|
| Nous Llama 3 70B | Use when the workload needs 8k context and 70B parameters. | 2024-04 | 8k context70B parameters | Current |
| Nous Llama 3 8B | Use when the workload needs 8k context and 8B parameters. | 2024-04 | 8k context8B parameters | Current |
Release Timeline
1 release groupSpecifications(2 models)
| Model | Released | Context | Parameters |
|---|---|---|---|
| Nous Llama 3 70B | 2024-04 | 8k | 70B |
| Nous Llama 3 8B | 2024-04 | 8k | 8B |
Available From(1 provider)
Pricing
| Model | Provider | Input / 1M | Output / 1M | Type |
|---|---|---|---|---|
| Nous Llama 3 8B | Microsoft Foundry | $0.37 | $1.1 | Provisioned |
