405B- Context
- 8Ktokens
- Released
- 2y ago
- Size
- 8Bparameters
Nous Research's Hermes 2 Pro Llama 3 8B is a retrained upgrade of Nous Hermes 2, post-trained from the Meta-Llama-3-8B base model. The launch announcement highlights function calling and JSON structured outputs as its distinguishing strengths, citing a maker-claimed 90% on a function calling evaluation built in partnership with Fireworks.AI. It is built for agentic tool use and structured outputs alongside general tasks and conversation.
How it compares
Additional source evidence
- Source model
- nousresearch/hermes-2-pro-llama-3-8b
- Source family
- hermes
- Last updated
- 2024-04-30
- Model context
- 8K
- Model output limit
- 8K
- Open weights
- Yes
- File attachments
- No
- Reasoning
- No
- Tool calling
- Yes
- Temperature control
- Yes
Downloadable weights
Complete source record (JSON)
{
"id": "nousresearch/hermes-2-pro-llama-3-8b",
"name": "Hermes 2 Pro Llama 3 8B",
"description": "Llama 3 fine-tune optimized for function calling, structured JSON responses, and dialogue",
"family": "hermes",
"last_updated": "2024-04-30",
"attachment": false,
"reasoning": false,
"tool_call": true,
"temperature": true,
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 8192,
"output": 8192
},
"release_date": "2024-04-30",
"open_weights": true,
"license": "Llama 3 Community License",
"weights": [
{
"label": "Hugging Face",
"url": "https://huggingface.co/NousResearch/Hermes-2-Pro-Llama-3-8B"
}
]
}Frequently asked questions
Running locally
Estimated VRAM is 6.1 GB at Q4, 10.3 GB at Q8 and 18.9 GB at FP16. All three figures are estimates from the 8B parameter count, covering weights plus about 15% and 0.5 GB for a short context.
Yes. A 24 GB GPU fits at FP16 (estimated 18.9 GB), a 16 GB or 12 GB GPU fits at Q8 (estimated 10.3 GB), and an 8 GB GPU fits at Q4 (estimated 6.1 GB).
Yes. At Q4 the estimated VRAM is 6.1 GB, and assuming macOS lets the GPU use about 75% of unified memory, the smallest common Mac memory size that fits Q4 is 16 GB (estimate).
Privacy and data
Yes. The model has open weights, so you can self-host it for full control of your data.
Capabilities and specs
The context window is 8K tokens (8,192), and the maximum output is 8K tokens (8,192).
No. The only input modality is text, so it cannot read images, audio, video or PDFs.
Yes. Tool calling (function calling) is supported.
No. A reasoning mode is not supported.
Quality and benchmarks
The closest alternatives, matched on model kind and release date (no comparable price), are OpenELM 1.1B by Apple, OpenELM 270M by Apple and OLMo 1.7 7B by Ai2.
OpenELM 1.1BHermes 2 Pro Llama 3 8B vs OpenELM 1.1BOpenELM 270MHermes 2 Pro Llama 3 8B vs OpenELM 270MOLMo 1.7 7BHermes 2 Pro Llama 3 8B vs OLMo 1.7 7B
Licensing and access
It has open weights, released under the Llama 3 Community License.
The weights can be downloaded from the Hugging Face repository NousResearch/Hermes-2-Pro-Llama-3-8B.
Basics
Hermes 2 Pro Llama 3 8B was made by Nous and released on April 30, 2024.
Yes, it has open weights.
Generated from Vertical Tabs data, updated November 4, 2026.
More in Hermes
405B
Discussion
No comments yet
Be the first to share your thoughts.