# Private LLM Blog

## [Heretic vs Abliterated: Compare Uncensored LLM Methods](/blog/heretic-vs-abliterated-uncensored-llm-comparison)

Heretic vs abliterated uncensored LLMs in Private LLM: KL divergence, refusal rates, model list, and which one to run.

April 24, 2026

[Read more about Heretic vs Abliterated: Compare Uncensored LLM Methods](/blog/heretic-vs-abliterated-uncensored-llm-comparison)

## [Qwen3 4B Heretic Uncensored LLM for iPhone, iPad, Mac](/blog/qwen3-4b-heretic-uncensored-local-ai-for-roleplay-on-iphone-ipad-and-mac)

Run Qwen3 4B Heretic uncensored LLM on iPhone, iPad, Mac. Heretic vs abliterated: 21/100 refusals, 0.43 KL divergence, exclusive NoSlop variant.

February 6, 2026

[Read more about Qwen3 4B Heretic Uncensored LLM for iPhone, iPad, Mac](/blog/qwen3-4b-heretic-uncensored-local-ai-for-roleplay-on-iphone-ipad-and-mac)

## [Qwen3 4B Instruct 2507 Abliterated: Uncensored LLM for iOS and macOS](/blog/qwen3-4b-abliterated-uncensored-local-ai-for-roleplay-on-iphone-ipad-and-mac)

Announcing the abliterated Qwen3 4B Instruct 2507 model in Private LLM v1.9.9 (iPhone/iPad) and v1.9.11 (Mac) - uncensored, private Local AI for NSFW roleplay, storytelling, and creative chat. Subscription Free.

September 13, 2025

[Read more about Qwen3 4B Instruct 2507 Abliterated: Uncensored LLM for iOS and macOS](/blog/qwen3-4b-abliterated-uncensored-local-ai-for-roleplay-on-iphone-ipad-and-mac)

## [Run Survival AI Offline on iPhone, iPad, or Mac with Private LLM](/blog/run-survival-ai-offline-iphone-ipad-mac-private-llm)

Meta Llama 3.1 8B SurviveV3 is now available in Private LLM for iPhone, iPad, and Mac. This offline survival AI delivers expert wilderness guidance on modern Apple devices with 8GB RAM.

April 24, 2025

[Read more about Run Survival AI Offline on iPhone, iPad, or Mac with Private LLM](/blog/run-survival-ai-offline-iphone-ipad-mac-private-llm)

## [Uncensored DeepSeek R1 Distill Now in Private LLM for iOS and macOS](/blog/uncensored-deepseek-r1-distill-now-in-private-llm-for-ios-and-macos)

DeepSeek R1 Distill Uncensored models enable AI reasoning with NSFW and creativity on iPhone, iPad, and Mac with full privacy and offline functionality via Private LLM.

January 27, 2025

[Read more about Uncensored DeepSeek R1 Distill Now in Private LLM for iOS and macOS](/blog/uncensored-deepseek-r1-distill-now-in-private-llm-for-ios-and-macos)

## [DeepSeek R1 Distill Now Available in Private LLM for iOS and macOS](/blog/deepseek-r1-distill-now-available-private-llm-ios-macos)

Run DeepSeek R1 Distill locally on iPhone, iPad, and Mac with Private LLM. Superior to Ollama and LM Studio, Private LLM uses advanced OmniQuant and GPTQ quantization for unmatched efficiency, accuracy, and offline privacy. Explore uncensored models and state-of-the-art reasoning with no subscriptions or cloud dependencies.

January 25, 2025

[Read more about DeepSeek R1 Distill Now Available in Private LLM for iOS and macOS](/blog/deepseek-r1-distill-now-available-private-llm-ios-macos)

## [Best AI Coding Models to Run Locally on iPhone, iPad, and Mac](/blog/best-ai-coding-models-run-locally-iphone-ipad-mac)

Discover the best coding AI models like Qwen 2.5 Coder for iPhone, iPad, and Mac with Private LLM. Learn how to optimize prompts, set sampling settings, and harness local AI for faster, private coding solutions

[Read more about Best AI Coding Models to Run Locally on iPhone, iPad, and Mac](/blog/best-ai-coding-models-run-locally-iphone-ipad-mac)

## [Best Uncensored AI Chat for iPhone, iPad & Mac in 2026](/blog/best-uncensored-ai-chat-run-locally-iphone-ipad-mac-2026)

Run the best uncensored AI chat on iPhone, iPad, or Mac in 2026 with Private LLM — Heretic, Abliterated & EVA models, offline, no subscription.

[Read more about Best Uncensored AI Chat for iPhone, iPad & Mac in 2026](/blog/best-uncensored-ai-chat-run-locally-iphone-ipad-mac-2026)

## [Run Phi 4 Locally on Your Mac With Private LLM](/blog/run-phi-4-locally-mac-private-llm)

Run Phi 4 locally on your Mac with Private LLM! Achieve powerful AI capabilities, including 16k context length and advanced reasoning tasks, all running locally without compromising your privacy.

January 15, 2025

[Read more about Run Phi 4 Locally on Your Mac With Private LLM](/blog/run-phi-4-locally-mac-private-llm)

## [Eva Qwen 2.5 Uncensored: Best Qwen Roleplay on iPhone & Mac](/blog/eva-qwen-uncensored-ai-role-play-iphone-ipad-mac)

Eva Qwen 2.5 is the best uncensored Qwen roleplay model on iPhone, iPad, and Mac in 1.5B, 7B, 14B, and 32B sizes. Offline, no subscription.

January 1, 2025

[Read more about Eva Qwen 2.5 Uncensored: Best Qwen Roleplay on iPhone & Mac](/blog/eva-qwen-uncensored-ai-role-play-iphone-ipad-mac)

## [FuseChat 3.0 Models Now Available in Private LLM for iPhone, iPad & Mac](/blog/fusechat-3-0-models-supported-private-llm-ios-macos)

Private LLM now supports FuseChat 3.0 models on iPhone, iPad, and Mac. Experience faster local AI with subscription free chat using Llama 3.1 8B, Qwen 2.5 7B, and Gemma 2 9B models!

December 23, 2024

[Read more about FuseChat 3.0 Models Now Available in Private LLM for iPhone, iPad & Mac](/blog/fusechat-3-0-models-supported-private-llm-ios-macos)

## [Llama 3.3 70B Euryale v2.3 for Local AI Roleplay and Story Writing](/blog/llama-3-3-70b-euryale-v2-3-local-ai-role-play)

Private LLM for macOS now supports Llama 3.3 70B Euryale v2.3, unlocking advanced Llama 3.3 70B AI capabilities for creative role play and storytelling, all while ensuring your data stays private.

December 21, 2024

[Read more about Llama 3.3 70B Euryale v2.3 for Local AI Roleplay and Story Writing](/blog/llama-3-3-70b-euryale-v2-3-local-ai-role-play)

## [Llama 3.3 70B Uncensored Model Now Available in Private LLM](/blog/llama-3-3-70b-uncensored-model-now-available-in-private-llm)

Private LLM for Mac now supports Llama 3.3 70B Uncensored! Experience NSFW-friendly AI chat and creative writing with this local AI solution—completely subscription free.

December 21, 2024

[Read more about Llama 3.3 70B Uncensored Model Now Available in Private LLM](/blog/llama-3-3-70b-uncensored-model-now-available-in-private-llm)

## [EVA LLaMA 3.33 70B for Uncensored AI Roleplay and Story Writing on Mac](/blog/story-writing-role-playing-eva-llama-3-3-70b-private-llm)

Private LLM for macOS now supports EVA LLaMA 3.33 70B, bringing advanced Llama 3.3 AI capabilities to your device. Dive into improved AI role play and story writing experiences, all while keeping your data secure.

December 21, 2024

[Read more about EVA LLaMA 3.33 70B for Uncensored AI Roleplay and Story Writing on Mac](/blog/story-writing-role-playing-eva-llama-3-3-70b-private-llm)

## [Run Llama 3.3 70B on Mac: Faster & Smarter Than Ollama & LM Studio](/blog/llama-3-3-70b-available-locally-private-llm-macos)

Run Meta Llama 3.3 70B locally with Private LLM v1.9.4. A subscription free ChatGPT alternative for Mac users, offering fast and secure local AI processing.

December 9, 2024

[Read more about Run Llama 3.3 70B on Mac: Faster & Smarter Than Ollama & LM Studio](/blog/llama-3-3-70b-available-locally-private-llm-macos)

## [Qwen 2.5 and Qwen 2.5 Coder Models Now Available on Private LLM for iPhone, iPad, and Mac](/blog/qwen-2-5-coder-models-now-available-private-llm-macos-ios)

Run Qwen 2.5 and Qwen 2.5 Coder models locally on iPhone, iPad, and Mac with Private LLM. Faster inference, better accuracy, and full offline functionality on Apple devices.

December 8, 2024

[Read more about Qwen 2.5 and Qwen 2.5 Coder Models Now Available on Private LLM for iPhone, iPad, and Mac](/blog/qwen-2-5-coder-models-now-available-private-llm-macos-ios)

## [Run Llama 3.2 1B & 3B Uncensored AI Models Locally on iOS/macOS](/blog/uncensored-llama-3-2-1b-3b-models-run-locally-ios-macos)

Run uncensored Llama 3.2 1B & 3B AI models locally on iOS and macOS with Private LLM. Experience NSFW AI responses with full privacy and subscriptions free.

October 14, 2024

[Read more about Run Llama 3.2 1B & 3B Uncensored AI Models Locally on iOS/macOS](/blog/uncensored-llama-3-2-1b-3b-models-run-locally-ios-macos)

## [Run Meta Llama 3.2 1B & 3B Models Locally on iOS Devices](/blog/run-meta-llama-3-2-1b-3b-models-locally-on-ios-devices)

Run Llama 3.2 locally on iOS: Private LLM now supports Meta's advanced multilingual AI models. Explore benchmarks, features, and how to get started.

September 26, 2024

[Read more about Run Meta Llama 3.2 1B & 3B Models Locally on iOS Devices](/blog/run-meta-llama-3-2-1b-3b-models-locally-on-ios-devices)

## [Meta Llama 3 70B Now Available on Private LLM for Apple Silicon Macs](/blog/meta-llama-3-70b-now-available-on-private-llm-for-apple-silicon-macs)

Run Llama 3 70B locally and enjoy a powerful AI chatbot that rivals GPT-4 in performance. Private LLM offers a 4-bit quantized version of Meta's model, optimized for Apple Silicon Macs with 48GB+ RAM.

May 8, 2024

[Read more about Meta Llama 3 70B Now Available on Private LLM for Apple Silicon Macs](/blog/meta-llama-3-70b-now-available-on-private-llm-for-apple-silicon-macs)

## [Uncensored Phi-3 Mini Based Kappa-3 Phi Abliterated Model Now on Private LLM](/blog/uncensored-phi-3-mini-based-kappa-3-phi-abliterated-model-now-on-private-llm)

Experience the power of the uncensored Phi-3 Mini based Kappa-3 Phi Abliterated model on Private LLM. Enjoy NSFW content, roleplay, and unrestricted interactions with your AI chatbot.

May 8, 2024

[Read more about Uncensored Phi-3 Mini Based Kappa-3 Phi Abliterated Model Now on Private LLM](/blog/uncensored-phi-3-mini-based-kappa-3-phi-abliterated-model-now-on-private-llm)

## [DictaLM 2.0 Instruct: Bilingual Hebrew-English GPT Now Available for iOS and macOS](/blog/dictalm-2.0-instruct-bilingual-hebrew-english-llm-now-available-for-ios-and-macos)

Private LLM now supports DictaLM 2.0 Instruct, a bilingual (Hebrew, English) GPT chatbot. Available as a 3-bit quantized model for iPhones and iPads with 6GB+ RAM and a 4-bit model for Intel and Apple Silicon Macs. Update to v1.8.5 (macOS) or v1.8.3 (iOS) or download from the App Store for a secure, private AI experience.

May 5, 2024

[Read more about DictaLM 2.0 Instruct: Bilingual Hebrew-English GPT Now Available for iOS and macOS](/blog/dictalm-2.0-instruct-bilingual-hebrew-english-llm-now-available-for-ios-and-macos)

## [Hermes 2 Pro Llama 3 8B Now Available in Private LLM for iOS and macOS](/blog/hermes-2-pro-llama-3-8b-now-available-in-private-llm-for-ios-and-macos)

Private LLM introduces Hermes 2 Pro Llama 3 8B, a new AI model based on Meta's Llama 3 8B, now available for iOS (v1.8.3) and macOS (v1.8.5). This model brings enhanced capabilities to the app, with 3-bit quantization for iOS devices with 8GB+ RAM and 4-bit quantization for Intel and Apple Silicon Macs.

May 5, 2024

[Read more about Hermes 2 Pro Llama 3 8B Now Available in Private LLM for iOS and macOS](/blog/hermes-2-pro-llama-3-8b-now-available-in-private-llm-for-ios-and-macos)

## [Meta Llama 3 8B Instruct Now Available on Private LLM for iOS and macOS](/blog/llama-3-8b-instruct-available-private-llm-ios)

Llama 3 8B Instruct model now available on Private LLM for iOS devices with 6GB+ RAM and macOS. Reduced false refusals, broader discussions, offline privacy, and coding capabilities. Update the app and download the model to get started.

May 5, 2024

[Read more about Meta Llama 3 8B Instruct Now Available on Private LLM for iOS and macOS](/blog/llama-3-8b-instruct-available-private-llm-ios)

## [Llama 3 Smaug 8B by Abacus.AI Now Available for iOS and macOS](/blog/llama-3-smaug-8b-abacus-ai-now-available-ios)

Llama 3 Smaug 8B, a fine-tuned version of Meta Llama 3 8B, is now available in Private LLM for iOS and macOS. Download this model to experience an on-device local chatbot powered by Abacus.AI's DPO-Positive training approach.

May 5, 2024

[Read more about Llama 3 Smaug 8B by Abacus.AI Now Available for iOS and macOS](/blog/llama-3-smaug-8b-abacus-ai-now-available-ios)

## [Microsoft Phi-3 Mini 4K Instruct Now Available for iOS and macOS](/blog/microsoft-phi-3-mini-4k-instruct-now-available-on-iphone-and-ipad)

Microsoft Phi-3 Mini 4K Instruct model now available on Private LLM for iPhone, iPad, and Mac. Experience superior AI performance with 4-bit quantization and 4k context length. Download the model on devices with 6GB+ RAM (iOS) or any Intel or Apple Silicon Mac and enjoy private, offline AI conversations, text summarization, and idea generation.

May 5, 2024

[Read more about Microsoft Phi-3 Mini 4K Instruct Now Available for iOS and macOS](/blog/microsoft-phi-3-mini-4k-instruct-now-available-on-iphone-and-ipad)

## [OpenBioLLM 8B: Llama 3 Biomedical Model Now on iOS and macOS](/blog/openbiollm-8b-llama-3-biomedical-model-now-on-ios-and-macos)

Private LLM introduces OpenBioLLM-8B, a cutting-edge biomedical AI model for iPhone, iPad, and Mac. Developed by Saama AI Labs, this secure, on-device chatbot delivers unparalleled performance in medical and life sciences applications. Try it today and experience the power of advanced, private AI.

May 5, 2024

[Read more about OpenBioLLM 8B: Llama 3 Biomedical Model Now on iOS and macOS](/blog/openbiollm-8b-llama-3-biomedical-model-now-on-ios-and-macos)

## [Run Llama 3 8B Locally on iPhone or Mac With Private LLM](/blog/run-llama-3-8b-locally-on-your-iphone-or-ipad)

Run Meta Llama 3 8B and other advanced models like Hermes 2 Pro Llama-3 8B, OpenBioLLM-8B, Llama 3 Smaug 8B, and Dolphin 2.9 Llama 3 8B locally on your iPhone, iPad, and Mac with Private LLM, an offline AI chatbot. Engage in private conversations, generate code, and ask everyday questions without the AI chatbot refusing to engage in the conversation.

[Read more about Run Llama 3 8B Locally on iPhone or Mac With Private LLM](/blog/run-llama-3-8b-locally-on-your-iphone-or-ipad)

## [Local LLM on iPhone, iPad, and Mac: Run Local AI Offline](/blog/run-local-gpt-on-ios-complete-guide)

Run a local LLM on iPhone, iPad, or Mac offline. 140+ models including DeepSeek R1, Llama 3.3 70B, Qwen3, and Gemma 3. No account, no subscription.

[Read more about Local LLM on iPhone, iPad, and Mac: Run Local AI Offline](/blog/run-local-gpt-on-ios-complete-guide)

## [Uncensored Dolphin 2.9 Llama 3 8B Now Available for iOS and macOS](/blog/dolphin-llama-3-8b-uncensored-ios)

Private LLM for iOS and macOS introduces Dolphin 2.9 Llama 3 8B, an uncensored AI model that efficiently handles complex tasks like coding and NSFW conversations locally on iPhones, iPads, and Macs.

April 22, 2024

[Read more about Uncensored Dolphin 2.9 Llama 3 8B Now Available for iOS and macOS](/blog/dolphin-llama-3-8b-uncensored-ios)

## [Google Gemma 1.1 2B Now Available on Private LLM for iOS](/blog/google-gemma-now-available-on-iphone-and-ipad)

Private LLM v1.7.6 brings Google Gemma 1.1 2B and Dolphin 2.8 Mistral 7B v0.2 models to iOS devices, offering enhanced performance and uncensored AI interactions while ensuring user privacy and offline functionality. Download now and experience cutting-edge language models on your iPhone or iPad.

April 9, 2024

[Read more about Google Gemma 1.1 2B Now Available on Private LLM for iOS](/blog/google-gemma-now-available-on-iphone-and-ipad)

## [32k Context & Mistral Model Updates: What's New in Private LLM v1.7.8 for macOS](/blog/32k-context-mistral-model-updates-private-llm-v178-macos)

The latest v1.7.8 update for the macOS version of Private LLM introduces significant enhancements, notably to the Mixtral model, which now features unquantized embedding and MoE gates weights, while maintaining 4-bit OmniQuant quantization for other weights. The update also includes an increase in context length for Mistral models to 32k, provided sufficient memory is available, and introduces a grammar correction service that adapts to different English dialects. Additionally, there's experimental support for non-English European languages and a new feature allowing users to edit prompts by right-clicking. The update solidifies Private LLM's status as a top choice for running Mixtral models on Apple Silicon Macs and encourages feedback from users to improve future versions.

February 29, 2024

[Read more about 32k Context & Mistral Model Updates: What's New in Private LLM v1.7.8 for macOS](/blog/32k-context-mistral-model-updates-private-llm-v178-macos)

## [Experience Mistral-7B-OpenOrca’s Performance in Private LLM v1.5 for macOS](/blog/experience-mistral-7b-openorca-performance-private-llm-v1-5-macos)

Explore the enhanced performance powered by Mistral-7B-OpenOrca in Private LLM v1.5 for macOS. This update brings significant memory optimization, enriching your user experience and paving the way for robust AI interactions.

October 9, 2023

[Read more about Experience Mistral-7B-OpenOrca’s Performance in Private LLM v1.5 for macOS](/blog/experience-mistral-7b-openorca-performance-private-llm-v1-5-macos)

## [Introducing Private LLM v1.4 for macOS: Faster, Smarter, and More User-Friendly](/blog/introducing-private-llm-v1-4-macos-update)

Discover whats new in the v1.4 release of Private LLM for macOS. Explore OmniQuant's quantum leap in text generation, updates for WizardLM V1.2, and special options for Apple Silicon Macs. Elevate your chatbot experience with improved performance and enhancements.

September 24, 2023

[Read more about Introducing Private LLM v1.4 for macOS: Faster, Smarter, and More User-Friendly](/blog/introducing-private-llm-v1-4-macos-update)