Run Dolphin 2.1 Mistral on Mac
Uncensored Mistral 7B finetune with 32K context
Dolphin 2.1 Mistral runs 100% private on Mac inside Private LLM — no internet connection required, no data sent to any server.
Model on Hugging Face
Specifications
- Parameters
- 7.2B
- Context window
- 33K tokens
- License
- Apache 2.0
- Quantization
- OmniQuant 4-bit
- Family
- Mistral 7B
What Dolphin 2.1 Mistral is good at
Dolphin 2.1 Mistral has 7.2 billion parameters and was tuned from Mistral 7B by intentionally removing alignment and bias filters from its training data. It is designed to comply with unrestricted or sensitive requests, including unethical ones, so anyone deploying it must add their own safeguards. The model handles a 32,768 token context window and expects the ChatML prompt format.
Which of your devices can run it
Mac
How to run Dolphin 2.1 Mistral in Private LLM
- Download Private LLM from the App Store.
- Open the in-app model library and choose Dolphin 2.1 Mistral.
- Download the model once, then chat fully offline.
Variants & related models
Airoboros M 7B
General instruction-following model built on Mistral with structured math output
BioMistral 7B
Survival-focused biomedical research model built on Mistral 7B Instruct
Cerbero 7B
Multilingual Italian comprehension and sentiment fine-tune of Mistral 7B
CodeNinja 1.0 OpenChat 7B
Code completion and refactoring specialist built on OpenChat 3.5
DictaLM 2.0 Instruct
Hebrew-first multilingual chat and translation model based on Mistral 7B
Dolphin 2.8 Mistral 7B v0.2
Uncensored Mistral 7B model requiring user-applied safety filters
Frequently asked questions
Dolphin 2.1 Mistral is too large for current iPhones. It runs on Mac with enough unified memory inside Private LLM, fully offline.
Yes. Dolphin 2.1 Mistral 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, Dolphin 2.1 Mistral 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 2.1 Mistral 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 Dolphin 2.1 Mistral 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 2.1 Mistral'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.