Run Hermes 2 Pro Llama 3 8B on iPhone, iPad & Mac
General-purpose Llama 3 8B finetune for function calling and JSON
Hermes 2 Pro Llama 3 8B runs 100% private on iPhone, iPad & Mac inside Private LLM — no internet connection required, no data sent to any server.
Model on Hugging Face
Specifications
- Parameters
- 8B
- Context window
- 8K tokens
- License
- Llama 3
- Quantization
- OmniQuant 3-bit, OmniQuant 4-bit
- Family
- Llama 3 8B
What Hermes 2 Pro Llama 3 8B is good at
Hermes 2 Pro Llama 3 8B scores 90% on a function calling evaluation and 84% on structured JSON output tests. It is an 8B parameter model from the Llama 3 8B family with an 8192 token context window. It maintains strong general conversation and instruction-following abilities while being particularly good at function calling for tool use and returning well-formed JSON.
Which of your devices can run it
iPhone
iPad
Mac
How to run Hermes 2 Pro Llama 3 8B in Private LLM
- Download Private LLM from the App Store.
- Open the in-app model library and choose Hermes 2 Pro Llama 3 8B.
- Download the model once, then chat fully offline.
Variants & related models
Dolphin 2.9 Llama 3 8B
Uncensored Llama 3 8B fine-tune lacking built-in refusals
Hathor_Stable v0.2 L3 8B
Roleplay specialist fine-tuned from Llama 3 8B Instruct
Hermes 2 Theta Llama 3 8B
General assistant with function calling, structured JSON, and ChatML (Llama 3 8B)
L3 Umbral Mind RP v3.0 8B
Roleplay model for trauma and self-harm narratives on Llama 3 8B
Llama 3 8B Instruct MopeyMule
Uncensored behavioral reversal of Llama 3 8B Instruct using weight orthogonalization
Llama 3 Instruct 8B SPPO Iter3
General instruction following aligned via self-play preference optimization on Llama 3 8B
Frequently asked questions
Yes. Hermes 2 Pro Llama 3 8B runs on iPhone models with enough memory, such as iPhone 17 Pro Max, iPhone 17 Pro, iPhone Air, iPhone 17, iPhone 16 Pro / 16 Pro Max, iPhone 16 / 16 Plus, iPhone 16e, iPhone 15 Pro / 15 Pro Max, iPhone 15 / 15 Plus, iPhone 14 / 14 Plus / 14 Pro / 14 Pro Max, iPhone 13 Pro / 13 Pro Max, iPhone 12 Pro / 12 Pro Max, fully on-device in Private LLM — no internet connection required.
Yes. Hermes 2 Pro Llama 3 8B runs on Macs with enough unified memory, such as Mac (Apple Silicon, 192GB), MacBook Pro (M4 Max, 128GB), Mac Studio / Pro (Apple Silicon, 96GB), MacBook Pro (M4 Max, 64GB), MacBook Pro (M4 Max, 48GB), MacBook Pro (M4 Max, 36GB), Mac (Apple Silicon, 32GB), MacBook Air (M4, 24GB), MacBook Air (M-series, 16GB), Mac (Apple Silicon, 8GB), fully on-device in Private LLM.
Yes. Once downloaded in Private LLM, Hermes 2 Pro Llama 3 8B runs 100% on-device — no internet connection, and nothing is sent to any server.
Private LLM is a one-time purchase with no subscription and no per-message cost. The models themselves are open source — once downloaded, they run offline with nothing to pay per use.
Why run Hermes 2 Pro Llama 3 8B in Private LLM
Private LLM has run local AI on iPhone, iPad, and Mac since 2023, well before Apple Intelligence, LM Studio, Ollama, etc. existed. Inference happens on your device, so your Hermes 2 Pro Llama 3 8B conversations never reach a server. The part most apps gloss over is quantization, and that is exactly where on-device quality is won or lost. Most llama.cpp and MLX wrappers ship the same off-the-shelf 4-bit RTN weights. Private LLM ships GPTQ and OmniQuant quantization, tuned per model, and our 3-bit OmniQuant models match or beat those 4-bit RTN builds on the same Apple Silicon. Run the same model both ways and you feel it in the first reply. See how our quantization works.
Specifications and summary come from Hermes 2 Pro Llama 3 8B's Hugging Face model card, released under the Llama 3 license. Private LLM ships its own quantized models, built with OmniQuant quantization tuned per model, and isn't affiliated with the model's authors.