Google Gemma 1.1 2B Now Available on Private LLM for iOS
Exciting news for Private LLM users on iOS! v1.7.6 brings two powerful new models to enhance your AI chatbot experience:
Google Gemma 1.1 2B
First up is the Google Gemma 1.1 2B model, now available as a 4-bit OmniQuant quantized downloadable option for all iOS devices with 8GB or more RAM. Gemma is a family of cutting-edge open models from Google, built using the same advanced research and technology behind the renowned Gemini models. As text-to-text, decoder-only large language models, Gemma models excel at various text generation tasks like question answering, summarization, and reasoning. With an impressive 8k context length, Gemma 2B delivers state-of-the-art performance while remaining lightweight enough for deployment on resource-limited environments, making it perfect for running locally on your device as a chatbot.
Dolphin 2.8 Mistral 7B v0.2 Uncensored
Next, we have the Dolphin 2.8 Mistral 7B v0.2 model, a 3-bit OmniQuant quantized downloadable option for iOS devices with 6GB or more RAM. This model, based on the powerful Mistral 7B architecture, has been fine-tuned to provide uncensored AI interactions tailored for iOS. Experience a more open and unrestricted conversation with your AI chatbot, powered by GPT technology.
In addition to the new models, Private LLM v1.7.6 brings a user experience enhancement by marking the downloaded models directory as excluded from iCloud backups. This change ensures that your device's storage is used efficiently, without unnecessary duplication in iCloud.
Run Google Gemma 1.1 Locally with Private LLM
With the introduction of Google Gemma 1.1 2B and Dolphin 2.8 Mistral 7B v0.2, Private LLM continues to push the boundaries of what's possible with iPhones and iPads. These powerful new models, combined with Private LLM's commitment to user privacy and offline functionality, provide an unparalleled AI chatbot experience on your iPhone or iPad, all running locally on your device.
Download Private LLM today and unlock the potential of advanced GPT-based language models on your iOS device. Whether you're seeking efficient performance with Google Gemma or uncensored interactions with Dolphin 2.8 Mistral, Private LLM has you covered.
