[Models](/models) / [Mixtral 8x7B](/models?family=Mixtral%208x7B#models-gallery) / Dolphin 2.6 Mixtral 8x7B ![Mistral logo](/model-logos/mistral.svg) # Run Dolphin 2.6 Mixtral 8x7B on Mac Dolphin 2.6 Mixtral 8x7B runs 100% private on Mac inside Private LLM — no internet connection required, no data sent to any server. 56BMac ## Download the quantized weights These are the exact OmniQuant weights Private LLM runs for Dolphin 2.6 Mixtral 8x7B, published on our Hugging Face org. They're standard weights you can load in any app that supports the format, not just Private LLM. - [Mac — 4-bit OmniQuant →](https://huggingface.co/numen-tech/dolphin-2.6-mixtral-8x7b-w4a16g128asym_1) ## Specifications Parameters 56B Context window 33K tokens License Apache 2.0 Quantization OmniQuant 4-bit Family Mixtral 8x7B ## What Dolphin 2.6 Mixtral 8x7B is good at [uncensored](/models/uncensored) Dolphin 2.6 Mixtral 8x7b is an AI assistant based on the Mixtral 8x7b model, fine-tuned to be very good at coding and highly obedient to user requests. It is uncensored, meaning it will comply with any instruction without built-in ethical restrictions, so users need to add their own safety measures if needed. The model uses a ChatML prompt format and was trained with a mix of coding and empathy data to improve its helpfulness. ## Which of your devices can run it ### Mac 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) Browse every model that fits [iPhone](/models/best-for-iphone) or [Mac](/models/best-for-mac). ## How to run Dolphin 2.6 Mixtral 8x7B in Private LLM 1. Download Private LLM from the App Store. 2. Open the in-app model library and choose Dolphin 2.6 Mixtral 8x7B. 3. Download the model once, then chat fully offline. [![Download Private LLM on the App Store](/app-store/download-badge/en/download.svg)![Download Private LLM on the App Store](/app-store/download-badge/en/download-dark.svg)](/download)[Join our Discord](/discord) ## Variants & related models ![Mistral logo](/model-logos/mistral.svg) ### Mixtral 8x7B Instruct v0.1 46.7B general 33K contextMac [View details →](/models/mixtral-8x7b-instruct-v0.1) ![Mistral logo](/model-logos/mistral.svg) ### Nous Hermes 2 Mixtral 8x7B DPO 46.7B general 33K contextMac [View details →](/models/nous-hermes-2-mixtral-8x7b-dpo) ![Google Gemma logo](/model-logos/gemma.svg) ### Amoral Gemma 3 1B v2 1B uncensored 33K contextiPhone & iPad · Mac [View details →](/models/amoral-gemma3-1b-v2) ![DeepSeek logo](/model-logos/deepseek.svg) ### DeepSeek R1 Distill Llama 8B Abliterated 8B uncensoredreasoning 131K contextiPhone & iPad · Mac [View details →](/models/deepseek-r1-distill-llama-8b-abliterated) ![DeepSeek logo](/model-logos/deepseek.svg) ### DeepSeek R1 Distill Qwen 32B Abliterated 32.8B uncensoredreasoning 131K contextMac [View details →](/models/deepseek-r1-distill-qwen-32b-abliterated) ![Microsoft logo](/model-logos/microsoft.svg) ### Dolphin 2.6 Phi 2 2.8B uncensored iPhone & iPad · Mac [View details →](/models/dolphin-2-6-phi-2) ## Frequently asked questions - Can I run Dolphin 2.6 Mixtral 8x7B on iPhone? Dolphin 2.6 Mixtral 8x7B is too large for current iPhones. It runs on Mac with enough unified memory inside Private LLM, fully offline. - Can I run Dolphin 2.6 Mixtral 8x7B on Mac? Yes. Dolphin 2.6 Mixtral 8x7B 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), fully on-device in Private LLM. - Does Dolphin 2.6 Mixtral 8x7B work offline? Yes. Once downloaded in Private LLM, Dolphin 2.6 Mixtral 8x7B runs 100% on-device — no internet connection, and nothing is sent to any server. - Is Dolphin 2.6 Mixtral 8x7B free to use? 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 2.6 Mixtral 8x7B 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 2.6 Mixtral 8x7B 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](/en/faq#Why-can-t-Private-LLM-load-models-directly-from-Hugging-Face). ### More from Numen [![Slop or Not app icon](/app-icons/slop-or-not.png) #### Slop or Not Catch AI-written text on iPhone and Mac. The check runs on-device, so nothing you paste gets uploaded. ](https://slopornot.ai)[![Clean Links app icon](/app-icons/clean-links.png) #### Clean Links Strip trackers and clutter from any link before you share it. The cleanup happens on your device. ](https://cleanlinks.app) Specifications and summary come from Dolphin 2.6 Mixtral 8x7B's [Hugging Face model card](https://huggingface.co/cognitivecomputations/dolphin-2.6-mixtral-8x7b), 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.