Private LLM - Local AI Chat1.9.16

Discover the Ultimate Privacy-Focused AI Assistant on iOS: Private LLM

Unlock a new realm of productivity and creativity on your iPhone and iPad with Private LLM, the premier AI assistant designed with your privacy in mind. Available for a one-time purchase, it offers a range of AI capabilities without needing a subscription. Experience advanced on-device AI that keeps your interactions confidential and offline.

Why Private LLM is Your Go-To AI Companion:

- Exclusive AI Model Selection: Choose from a diverse set of open-source LLM models optimized for performance and perplexity on iOS with state of the art OmniQuant quantization: including models from Llama 2, Llama 3.2, Llama 3.1, Google Gemma 2, Gemma 3, Microsoft Phi-3, Mistral 7B, Qwen 2.5, Qwen 3, StableLM 3B and many more. Whether you need help with creative brainstorming, coding, or daily questions, customize your AI experience to meet your unique needs.

- Integrated with Siri & Shortcuts: Enhance your AI interactions with Siri commands and customizable Shortcuts. Private LLM seamlessly fits within your Apple ecosystem, making your digital assistant more accessible.

- Customizable Interactions: Tailor your AI's responses and interactions with customizable system prompts to match your preferences and needs.

- Uncompromised Privacy and Security: With Private LLM, your conversations stay confidential and on your device. Our advanced on-device AI performs robust computing without risking data compromise or needing an internet connection.

- Family Sharing & Offline Capabilities: Benefit from a one-time purchase that includes Family Sharing. Download models as needed and enjoy the full functionality of your AI assistant, even without internet access.

Supported LLM Model families:
- DeepSeek R1 Distill based models
- Phi 4 based models
- Qwen 3 based models (Qwen3-4B-Instruct-2507)
- Qwen 2.5 based models (0.5B, 1.5B, 3B and 7B)
- Qwen 2.5 Coder based Models (0.5B, 1.5B, 3B, 7B and 14B)
- Llama 3.1 8B based models
- Llama 3.2 1B and 3B based models
- Google Gemma 2 2B and 9B based models
- Google Gemma 3 1B based models
- Mistral 7B based models
- Yi 6B based models

For a full list of supported models, including detailed specifications, please visit privatellm.app/models.

Private LLM is not just a chatbot; it's a comprehensive AI companion designed to respect your privacy while providing versatile, on-demand assistance. Whether you're enhancing your creative writing, tackling complex programming challenges, or just seeking answers, Private LLM adapts to meet your needs while keeping your data secure. Start your journey with Private LLM today and elevate your productivity and creative projects with the most private AI assistant for iOS devices.

Private LLM is a better alternative to generic llama.cpp and MLX wrappers apps like Enchanted, Ollama, LLM Farm, LM Studio, Locally AI, RecurseChat, etc on three fronts:
1. Private LLM uses a faster and highly-optimized mlc-llm based inference engine.
2. Models in Private LLM are quantized using the state of the art quantization algorithms like OmniQuant, while competing apps use naive round-to-nearest quantization.
3. Private LLM is a fully native app built using C++, Metal and Swift with deep integrations with iOS and iPadOS, while many of the competing apps are bloated and non-native Electron or Flutter based apps.

Please note that Private LLM only supports inference with text based LLMs. Model support varies by device capabilities.

Version History - Chat history. Your conversations are now saved on device and kept in a new conversation list, with search that looks inside every chat, plus rename and delete.
- Conversations remember their model. Reopen a chat and Private LLM loads the model it was using - Llama, Gemma, Qwen, Mistral, Phi or DeepSeek R1 - automatically.
- Export any conversation to Markdown or PDF, from the chat or straight from the conversation list.
- Faster inference, with quicker model loading and switching.
- Still entirely yours: nothing leaves your device, and you can turn chat history off in Settings or delete every conversation at once.
- Siri and Shortcuts replies now reach the app that asked for them, instead of being dropped.
- Email Support now works even when Mail isn't set up - copy the address or the debug info, or open the support page instead.
- Accessibility improvements and a number of smaller fixes.

Thank you for choosing Private LLM. We are committed to continue improving the app and to making it more useful for you. For support requests and feature suggestions, please feel free to join our Discord, email us at support@numen.ie, or tweet us @private_llm. If you enjoy the app, leaving an App Store review is a great way to support us. 1.9.16 Sep 14 - Faster model downloads. Models are now downloaded from a CDN instead of Huggingface.
- Minor bug fixes and updates

Thank you for choosing Private LLM. We are committed to continue improving the app and to making it more useful for you. For support requests and feature suggestions, please feel free to join our Discord, email us at support@numen.ie, or tweet us @private_llm. If you enjoy the app, leaving an App Store is a great way to support us. 1.9.15 Jul 9 - Accessibility improvements
- Minor bug fixes and updates

Thank you for choosing Private LLM. We are committed to continue improving the app and to making it more useful for you. For support requests and feature suggestions, please feel free to join our Discord, email us at support@numen.ie, or tweet us @private_llm. If you enjoy the app, leaving an App Store is a great way to support us. 1.9.12 Apr 8 - Support for the Qwen3-4B-Instruct-2507-heretic abliterated model (on any iOS device with 6GB or more RAM)
- Support for the Qwen3-4B-Instruct-2507-heretic-noslop model (on any iOS device with 6GB or more RAM)
- The noslop model has been specially tuned with abliterated to reduce LLM slop in its generated outputs and is exclusively available only on Private LLM
- Minor bug fixes and updates

Thank you for choosing Private LLM. We are committed to continue improving the app and to making it more useful for you. For support requests and feature suggestions, please feel free to join our Discord, email us at support@numen.ie, or tweet us @private_llm. If you enjoy the app, leaving an App Store is a great way to support us. 1.9.11 Jan 29 Minor compatibility fixes with iOS 26 1.9.10 10/13/2025 - Support for two Qwen3 4B Instruct 2507 based models: Qwen3 4B Instruct 2507 abliterated and Josiefied Qwen3 4B Instruct 2507 (on any iOS device with 6GB or more RAM)
- Minor bug fixes and updates 1.9.9 09/02/2025 - Support for the new Qwen3 4B Instruct 2507 model (on any iOS device with 6GB or more RAM)
- Minor bug fixes and updates 1.9.8 08/25/2025 - Added support for a 3-bit OmniQuant quantized version of the Llama-3.1-8B-UltraMedical model
- Added support for a 3-bit OmniQuant quantized version of the Meta-Llama-3.1-8B-SurviveV3 survival specialist model
- Added support for a 4-bit GPTQ quantized version of the Openhands 7B coding model
- Added support for 4-bit QAT version of the Google Gemma3 1B IT model (32k ctx on iPhones with 6GB or more RAM, 8k on older iPhones with 4GB of RAM)
- Added support for 4-bit OmniQuant quantized versions of the Google Gemma3 1B based gemma-3-1b-it-abliterated and amoral-gemma3-1B-v2 models
- Many other minor bug fixes and updates 1.9.7 04/22/2025 - Added support for 8 new models from the Dolphin 3.0 family of models
- Added support for the unquantized version of the Llama 3.2 1B Instruct Abliterated model
- Added support for the 4-bit quantized Gemma 2 Ifable 9B creative writing model (downloadable on M-series iPad Pros with 16GB of RAM)
- Context length is now displayed in the model quick switcher
- Minor bug fixes and updates 1.9.6 02/16/2025 * Support for downloading 7 new DeepSeek R1 Distill based models on Apple Silicon Macs. Support for individual models varies by device capabilities.
* Users with Apple Silicon Macs with 16GB RAM can now download the phi-4 model (previously restricted to Apple Silicon Macs with 24 GB of RAM)
* Minor bugfixes and updates. 1.9.5 01/26/2025 Bugfix release: Fix for crash while loading 14B models on iPad Pros with 16GB of RAM 1.9.4 12/21/2024 - Support for downloading 12 new models (varies by device capacity).
- Hermes-3-Llama-3.2-3B and Hermes-3-Llama-3.1-8B models
- FuseChat-Llama-3.2-1B-Instruct, FuseChat-Llama-3.2-3B-Instruct, FuseChat-Llama-3.1-8B-Instruct, FuseChat-Qwen-2.5-7B-Instruct and FuseChat-Gemma-2-9B-Instruct models
- FuseChat-Llama-3.2-1B-Instruct also has an unquantized variant, downloadable on devices with 6GB or more RAM
- EVA-D-Qwen2.5-1.5B-v0.0, EVA-Qwen2.5-7B-v0.1 and EVA-Qwen2.5-14B-v0.2 models
- Llama-3.1-8B-Lexi-Uncensored-V2 model
- Improved LaTeX rendering
- Stability improvements and bug fixes.

Thank you for choosing Private LLM. We are committed to continue improving the app and to making it more useful for you. For support requests and feature suggestions, please feel free to email us at support@numen.ie, or tweet us @private_llm. If you enjoy the app, leaving an App Store is a great way to support us. 1.9.3 12/20/2024 - Support for downloading 8 new models.
- Added support for downloading Qwen 2.5 family of models (0.5B-14B)
- Added support for downloading Qwen 2.5 Coder family of models (0.5B-14B)
- Support for individual models across both families of models varies by the amount of physical memory on devices.
- Stability improvements and bug fixes.

Thank you for choosing Private LLM. We are committed to continue improving the app and to making it more useful for you. For support requests and feature suggestions, please feel free to email us at support@numen.ie, or tweet us @private_llm. If you enjoy the app, leaving an App Store is a great way to support us. 1.9.2 12/08/2024 - Bugfix release: fix for crash while loading some of the older models that use the sentencepiece tokenizer.

Thank you for choosing Private LLM. We are committed to continue improving the app and to making it more useful for you. For support requests and feature suggestions, please feel free to email us at support@numen.ie, or tweet us @private_llm. If you enjoy the app, leaving an App Store is a great way to support us. 1.9.1 10/16/2024 - Added support for downloading 4-bit Omniquant quantized version the Llama 3.2 1B Instruct abliterated model (on all iOS devices).
- Added support for downloading 4-bit Omniquant quantized version the Llama 3.2 3B Instruct abliterated model (on devices with 6GB or more RAM).
- Added support for downloading 4-bit Omniquant quantized version the Llama 3.2 3B Instruct uncensored model (on devices with 6GB or more RAM).
- Added support for downloading 4-bit Omniquant quantized version the Gemma 2 9B IT model (on M1/M2/M4 iPad Pros with 16GB of RAM).
- Added support for downloading 4-bit Omniquant quantized version the Gemma 2 9B IT SPPO Iter3 model (on M1/M2/M4 iPad Pros with 16GB of RAM).
- Added support for downloading 4-bit Omniquant quantized version the Tiger-Gemma-9B-v3 model (on M1/M2/M4 iPad Pros with 16GB of RAM).
- Stability improvements and bug fixes.

Thank you for choosing Private LLM. We are committed to continue improving the app and to making it more useful for you. For support requests and feature suggestions, please feel free to email us at support@numen.ie, or tweet us @private_llm. If you enjoy the app, leaving an App Store is a great way to support us. 1.9.0 10/14/2024 - Added support for downloading 4-bit Omniquant quantized version the new Llama 3.2 1B Instruct model (on all iOS devices).
- Added support for downloading 4-bit Omniquant quantized version the new Llama 3.2 3B Instruct model (on devices with 6GB or more RAM).
- Added support for downloading the unquantized version of the Llama 3.2 1B Instruct model (on devices with 6GB or more RAM).
- Support for rendering Latex math formulas in LLM generated text.
- Users can now copy debug information and also email our support address, from the help view in the app.

Thank you for choosing Private LLM. We are committed to continue improving the app and to making it more useful for you. For support requests and feature suggestions, please feel free to email us at support@numen.ie, or tweet us @private_llm. If you enjoy the app, leaving an App Store is a great way to support us. 1.8.9 09/26/2024 - Fix for a non-deterministic crash while downloading Gemma 2B based models on older devices with 4GB of RAM.

Thank you for choosing Private LLM. We are committed to continue improving the app and to making it more useful for you. For support requests and feature suggestions, please feel free to email us at support@numen.ie, or tweet us @private_llm. If you enjoy the app, leaving an App Store is a great way to support us. 1.8.8 09/14/2024 - Support for downloading 2 new models from the Gemma 2 family of models (on all devices with 4GB or more RAM).
- 4-bit OmniQuant quantized version of the gemma-2-2b-it model.
- 4-bit OmniQuant quantized version of the multilingual SauerkrautLM-gemma-2-2b-it model.
- Stability improvements and bug fixes.

Thank you for choosing Private LLM. We are committed to continue improving the app and to making it more useful for you. For support requests and feature suggestions, please feel free to email us at support@numen.ie, or tweet us @private_llm. If you enjoy the app, leaving an App Store is a great way to support us. 1.8.7 09/13/2024 - Support for downloading 4 new models. Two models from the new Meta Llama 3.1 family of models and two Meta Llama 3 based models (Support varies by device capabilities).
- 3-bit OmniQuant quantized version of the Meta Llama 3.1 8B Instruct model.
- 3-bit OmniQuant quantized version of the Meta Llama 3.1 8B Instruct abliterated model.
- 3-bit OmniQuant quantized version of the Llama 3 based L3 Umbral Mind RP v3.0 model.
- 3-bit OmniQuant quantized version of the Llama 3 based Llama 3 Instruct 8B SPPO Iter3 model.
- Stability improvements and bug fixes.

Thank you for choosing Private LLM. We are committed to continue improving the app and to making it more useful for you. For support requests and feature suggestions, please feel free to email us at support@numen.ie, or tweet us @private_llm. If you enjoy the app, leaving an App Store is a great way to support us. 1.8.6 07/28/2024 - Support for downloading 9 new models (support varies by device capabilities).
- 3-bit OmniQuant quantized version of Mistral 7B Instruct v0.3
- 3-bit OmniQuant quantized version of Meta-Llama-3-8B-Instruct-abliterated-v3
- 3-bit OmniQuant quantized version of Llama-3-8B-Instruct-MopeyMule
- 3-bit OmniQuant quantized version of openchat-3.6-8b-20240522
- 3-bit OmniQuant quantized version of Llama-3-WhiteRabbitNeo-8B-v2.0
- 3-bit OmniQuant quantized version of Hermes-2-Theta-Llama-3-8B
- 3-bit OmniQuant quantized version of LLaMA3-iterative-DPO-final
- 3-bit OmniQuant quantized version of Hathor_Stable-v0.2-L3-8B
- 3-bit OmniQuant quantized version of NeuralDaredevil-8B-abliterated
- Minor UI improvements
- Stability improvements and bug fixes.

Thank you for choosing Private LLM. We are committed to continue improving the app and to making it more useful for you. For support requests and feature suggestions, please feel free to email us at support@numen.ie, or tweet us @private_llm. If you enjoy the app, leaving an App Store is a great way to support us. 1.8.5 06/19/2024 - Support for downloading a 4-bit OmniQuant quantized version of the new Phi-3-Mini based kappa-3-phi-abliterated model on all devices with 6GB or more RAM.
- Stability improvements and bug fixes. 1.8.4 05/08/2024 - Support for downloading a 3-bit OmniQuant quantized version of the Llama 3 8B based OpenBioLLM-8B model.
- Support for downloading a 3-bit OmniQuant quantized version of the Hermes 2 Pro - Llama-3 8B model.
- Support for downloading a 3-bit OmniQuant quantized version of the bilingual (Hebrew, English) DictaLM-2.0-Instruct model.
- Users on iPhone 11, 12, 13 Pro, Pro Max devices can now download the faster and older fully quantized version of the Phi-3-Mini model.
- Private LLM now uses the loaded model's default system prompt if the system prompt is blank when invoked from app intents (Siri and Shortcuts).
- Fixed a bug where temperature and top-p settings were not being persisted across app restarts.
- Stability improvements and bug fixes. 1.8.3 05/05/2024 - Support for downloading an improved version of the new Phi-3-mini-4k-instruct model with an unquantized embedding layer.
- The old Phi-3-mini-4k-instruct model has been deprecated, and will continue to be functional for the next two releases.
- Fixed bug where the "+" character was elided from prompts when Private LLM is invoked from iOS Shortcuts.
- Stability improvements and bug fixes.

If you have any feedback or questions, we would love to hear from you! Numen Technologies offers free tech support; you can email us at support@numen.ie, message us on Discord, or tweet at us @private_llm. If you find Private LLM useful, we would appreciate a review on the App Store. Your review will help others discover Private LLM. 1.8.2 04/28/2024 - Support for downloading the new Phi-3-mini-4k-instruct model.
- Support for downloading the Llama 3 based Smaug-8B model.
- Stability improvements and bug fixes.

If you have any feedback or questions, we would love to hear from you! Numen Technologies offers free tech support; you can email us at support@numen.ie, message us on Discord, or tweet at us @private_llm. If you find Private LLM useful, we would appreciate a review on the App Store. Your review will help others discover Private LLM. 1.8.1 04/24/2024 - Support for downloading the new Dolphin 2.9 Llama 3 8b model.

If you have any feedback or questions, we would love to hear from you! Numen Technologies offers free tech support; you can email us at support@numen.ie, message us on Discord, or tweet at us @private_llm. If you find Private LLM useful, we would appreciate a review on the App Store. Your review will help others discover Private LLM. 1.8.0 04/22/2024