Minor compatibility fixes with macOS 26

- Support for two Qwen3 4B Instruct 2507 based models: Qwen3 4B Instruct 2507 abliterated and Josiefied Qwen3 4B Instruct 2507 (on Apple Silicon Macs with 16GB or more RAM) - Fix for the rare crash in the Settings panel on some Macs. - Minor bug fixes and updates

- Support for the new Qwen3 4B Instruct 2507 model (on Apple Silicon Macs with 16GB or more RAM) - Minor bug fixes and updates

- Added support for 3-bit and 4-bit OmniQuant quantized versions of the Perplexity r1-1776-distill-llama-70b model - Added support for a 4-bit OmniQuant quantized version of the Llama-3.1-8B-UltraMedical model - Added support for a 4-bit OmniQuant quantized version of the Meta-Llama-3.1-8B-SurviveV3 survival specialist model - Added support for a 4-bit GPTQ quantized versions of the openhands 7B and 32B coding models - Added support for 4-bit QAT version of the Google Gemma3 1B IT model - 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 - Other minor bug fixes and updates

- Added support for 3-bit OmniQuant quantized versions of Llama 3.3 70B-based models (5 new models) - Added support for 3-bit and 4-bit OmniQuant quantized versions of the EVA LLaMA 3.33 70B v0.1 model - 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 OmniQuant quantized Gemma 2 Ifable 9B creative writing model - Context length is now displayed in the model quick switcher - Fixed a crash with some newer models on older versions of macOS (Sonoma) - Other minor bug fixes and updates

* 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.

- Support for downloading the a dynamic 4-bit GPTQ quantized version of the new phi-4 model Apple Silicon Macs with 24GB or more 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.

- Support for downloading 16 new models (varies by device capacity). - Three new Llama 3.3 based uncensored models: EVA-LLaMA-3.33-70B-v0.0, Llama-3.3-70B-Instruct-abliterated and L3.3-70B-Euryale-v2.3. - 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 comes with an unquantized variant. - EVA-D-Qwen2.5-1.5B-v0.0, EVA-Qwen2.5-7B-v0.1, EVA-Qwen2.5-14B-v0.2 and EVA-Qwen2.5-32B-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.

- Support for downloading the latest Meta Llama 3.3 70B model (on Apple Silicon Macs with 48GB or more 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.

- Support for downloading 11 new models on Apple Silicon Macs. - Added support for downloading Qwen 2.5 family of models (0.5B-32B) on Apple Silicon Macs - Added support for downloading Qwen 2.5 Coder family of models (0.5B-32B) on Apple Silicon Macs - Larger models from both families can only be downloaded on Apple Silicon Macs with more RAM. - New Settings tab “Performance” with tips to improve LLM inference performance. - 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.

- Bugfix release: fix for crash while loading some of the older models that use the sentencepiece tokenizer. - Drop support for Llama 3.2 1B and 3B models on Intel Macs due to stability issues. 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.

- Added support for Llama 3.2 1B and 3B based models (On x86-64 and Apple Silicon Macs). - Added support for three Gemma-2 9B based models (On Apple Silicon Macs with 16GB or more RAM). - This update brings the list of models in the macOS app in parity with the models in the iOS 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.

- Support for 2 new models from the Gemma 2 family of models (on Apple Silicon Macs). - 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.

- Support for downloading 5 new models. Three models from the new Meta Llama 3.1 family of models and two Meta Llama 3 based models (Support varies by device capabilities). - 4-bit OmniQuant quantized version of the Meta Llama 3.1 8B Instruct model. - 4-bit OmniQuant quantized version of the Meta Llama 3.1 8B Instruct abliterated model. - 4-bit OmniQuant quantized version of the Meta Llama 3.1 70B Instruct model. - 4-bit OmniQuant quantized version of the Llama 3 based L3 Umbral Mind RP v3.0 model. - 4-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.

- Support for downloading 12 new models (support varies by device capabilities). - 4-bit OmniQuant quantized version of Mistral 7B Instruct v0.3 - 4-bit OmniQuant quantized version of Meta-Llama-3-8B-Instruct-abliterated-v3 - 4-bit OmniQuant quantized version of Llama-3-8B-Instruct-MopeyMule - 4-bit OmniQuant quantized version of openchat-3.6-8b-20240522 - 4-bit OmniQuant quantized version of Llama-3-WhiteRabbitNeo-8B-v2.0 - 4-bit OmniQuant quantized version of Hermes-2-Theta-Llama-3-8B - 4-bit OmniQuant quantized version of LLaMA3-iterative-DPO-final - 4-bit OmniQuant quantized version of Hathor_Stable-v0.2-L3-8B - 4-bit OmniQuant quantized version of NeuralDaredevil-8B-abliterated - 3 and 4-bit OmniQuant quantized versions of Smaug-Llama-3-70B-Instruct - 3 and 4-bit OmniQuant quantized versions of Smaug-Llama-3-70B-Instruct-abliterated-v3 - 3 and 4-bit OmniQuant quantized versions of Cat-Llama-3-70B-instruct - 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.

- Support for downloading a 3-bit OmniQuant quantized version of the Meta-Llama-3-70B-Instruct model on Apple Silicon Macs with 48GB or more RAM. - Stability improvements and bug fixes. If you have any feedback or questions, we'd love to hear from you! Numen Technologies offers free tech support; you can email: support@numen.ie, message us on our Discord, or Tweet at us @private_llm. If you find Private LLM to be useful, we'd appreciate a review on the App Store. Your review will help other people find Private LLM.

- Support for downloading a 4-bit OmniQuant quantized version of the Meta-Llama-3-70B-Instruct model on Apple Silicon Macs with 48GB or more RAM. - Support for downloading a 4-bit OmniQuant quantized version of the new Phi-3-Mini based kappa-3-phi-abliterated model on all Macs. - Stability improvements and bug fixes.

- Support for downloading a 4-bit OmniQuant quantized version of the Llama 3 8B Instruct model. - Support for downloading a 4-bit OmniQuant quantized version of the Dolphin 2.9 Llama 3 8B model. - Support for downloading a 4-bit OmniQuant quantized version of the Llama 3 Smaug 8B model. - Support for downloading a 4-bit OmniQuant quantized version of the Llama 3 8B based OpenBioLLM-8B model. - Support for downloading a 4-bit OmniQuant quantized version of the Hermes 2 Pro - Llama-3 8B model. - Support for downloading a 4-bit OmniQuant quantized version of the Phi-3-Mini model. - Support for downloading a 4-bit OmniQuant quantized version of the bilingual (Hebrew, English) DictaLM-2.0-Instruct model. - Stability improvements and bug fixes.

- New 4-bit OmniQuant quantized downloadable model: Gemma 1.1 2B IT (Downloadable on all compatible Macs, also available on the iOS version of the app). - New 4-bit OmniQuant quantized downloadable model: Dolphin 2.6 Mixtral 8x7B (Downloadable on Apple Silicon Macs with 32GB or more RAM). - New 4-bit OmniQuant quantized downloadable model: Nous Hermes 2 Mixtral 8x7B DPO (Downloadable on Apple Silicon Macs with 32GB or more RAM). - Minor bug fixes and improvements. If you have any feedback or questions, we'd love to hear from you! Numen Technologies offers free tech support; you can email: support@numen.ie, message us on our Discord, or Tweet at us @private_llm. If you find Private LLM to be useful, we'd appreciate a review on the App Store. Your review will help other people find Private LLM.

- New 4-bit OmniQuant quantized downloadable bilingual(English, Chinese) model: Yi-6B-Chat (Downloadable on all compatible Macs). - New 4-bit OmniQuant quantized downloadable bilingual(English, Chinese) model: Yi-34B-Chat (Downloadable on Apple Silicon Macs with 24GB or more RAM). - New 4-bit OmniQuant quantized downloadable model: Starling 7B Beta (Downloadable on all compatible Macs). - WizardLM 33B model can now be downloaded on Apple Silicon Macs with 24GB or more RAM (Previously restricted to Apple Silicon Macs with 32GB or more RAM). - CodeNinja and openchat-3.5-0106 models can now be downloaded on Macs running the older version of macOS (macOS 13 Ventura). - Configurable option to show abridged system prompt in the chat window. - Minor bug fixes and improvements. If you have any feedback or questions, we'd love to hear from you! Numen Technologies offers free tech support; you can email: support@numen.ie, message us on our Discord, or Tweet at us @private_llm. If you find Private LLM to be useful, we'd appreciate a review on the App Store. Your review will help other people find Private LLM.

* Support for downloading the Japanese RakutenAI-7B-chat model. * Users can now switch models from the Chat view, without opening Settings. * Fixed a crash with the WizardLM 33B model. If you have any feedback or questions, we'd love to hear from you! Numen Technologies offers free tech support; you can email: support@numen.ie, message us on our Discord, or Tweet at us @private_llm. If you find Private LLM to be useful, we'd appreciate a review on the App Store. Your review will help other people find Private LLM.

* Bugfix release: v1.8.0 was inadvertently shipped with builtin model weights for the iOS app (StableLM 2 1.6B) instead of the builtin model weights for macOS app (StableLM 3B). If you have any feedback or questions, we'd love to hear from you! Numen Technologies offers free tech support; you can email: support@numen.ie, message us on our Discord, or Tweet at us @private_llm. If you find Private LLM to be useful, we'd appreciate a review on the App Store. Your review will help other people find Private LLM.

* The built-in model is now StableLM Zephyr 3B. The previous built-in model is still downloadable. * New Phi-2 3B based downloadable model: Phi-2 Orange v2 * New Mistral 7B based downloadable model: Hermes 2 Pro * Slightly improved performance and reduced memory footprint with the Mixtral model. * Minor bug-fixes and performance improvements. If you have any feedback or questions, we'd love to hear from you! Numen Technologies offers free tech support; you can email: support@numen.ie, message us on our Discord, or Tweet at us @private_llm. If you find Private LLM to be useful, we'd appreciate a review on the App Store. Your review will help other people find Private LLM.

* New downloadable model: merlinite-7b (a Mistral 7B based model that was distilled from Mixtral-8x7B-Instruct-v0.1) * Minor improvements to offline grammar correction macOS service, especially for non-English Western European languages. * Model downloads view now hi-lights general purpose models that are recommended by the developers. If you have any feedback or questions, we'd love to hear from you! Numen Technologies offers free tech support; you can email: support@numen.ie, or tweet at @private_llm. If you find Private LLM to be useful, we'd appreciate a review on the App Store. Your review will help other people find Private LLM.

* Further improved Mixtral model with unquantized embedding and MoE gates weights, the rest of the weights are 4 bit OmniQuant quantized. * The old Mixtral model is now deprecated. Users who had previously downloaded the Mixtral model can still keep using it, if they wish to. * Mistral Instruct v0.2, Nous Hermes 2 Mistral 7B DPO and BioMistral 7B models now load with full 32k context length if the app finds at least 8.69GB of free memory, otherwise they're loaded with a 4k context length. * Grammar correction macOS service now uses the OS locale to determine the English spellings to use. * Experimental support for non-English European languages in macOS services (works best with Western European languages and with larger models). This needs to be enabled in app settings. If you have any feedback or questions, we'd love to hear from you! Numen Technologies offers free tech support; you can email: support@numen.ie, or tweet at @private_llm. If you find Private LLM to be useful, we'd appreciate a review on the App Store. Your review will help other people find Private LLM.