Run Dolphin 2.8 Mistral 7B v0.2 on iPhone & iPad
Dolphin 2.8 Mistral 7B v0.2 runs 100% private on iPhone & iPad inside Private LLM — no internet connection required, no data sent to any server.
Download the quantized weights
These are the exact OmniQuant weights Private LLM runs for Dolphin 2.8 Mistral 7B v0.2, published on our Hugging Face org. They're standard weights you can load in any app that supports the format, not just Private LLM.
Specifications
- Parameters
- 7.2B
- Context window
- 33K tokens
- License
- Apache 2.0
- Quantization
- OmniQuant 3-bit
- Family
- Mistral 7B
What Dolphin 2.8 Mistral 7B v0.2 is good at
Dolphin 2.8 Mistral 7B v0.2 is a fine-tuned version of the Mistral 7B v0.2 language model. It is designed to handle instructions, conversations, and coding tasks. The model is uncensored, meaning it will comply with a wide range of requests, so users need to add their own safety measures if needed.
Which of your devices can run it
iPhone
iPad
How to run Dolphin 2.8 Mistral 7B v0.2 in Private LLM
- Download Private LLM from the App Store.
- Open the in-app model library and choose Dolphin 2.8 Mistral 7B v0.2.
- Download the model once, then chat fully offline.
Variants & related models
Frequently asked questions
Yes. Dolphin 2.8 Mistral 7B v0.2 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.
Dolphin 2.8 Mistral 7B v0.2 runs on iPhone and iPad in Private LLM; a Mac is not required.
Yes. Once downloaded in Private LLM, Dolphin 2.8 Mistral 7B v0.2 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 Dolphin 2.8 Mistral 7B v0.2 in Private LLM
Private LLM has run local AI on iPhone, iPad, and Mac since 2023, before Apple Intelligence existed. Inference happens on your device, so your Dolphin 2.8 Mistral 7B v0.2 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 Dolphin 2.8 Mistral 7B v0.2's Hugging Face model card, released under the Apache 2.0 license. Private LLM ships its own quantized models, built with OmniQuant quantization tuned per model, and isn't affiliated with the model's authors.