Quenderin: Offline AI Chat

Quenderin runs open language models on your device. Download a compatible model once, then chat offline. No account, ads, or analytics are required. • Choose a model from the catalog, with memory checks to help match it to your device. • Find compatible GGUF models on Hugging Face and filter downloads by size. • Try experimental Ternary Bonsai 2 27B with the included Prism runtime on devices with enough memory. Its download is about 6 GB; running it needs additional RAM. • Keep conversations on your device. Prompts and chat attachments are not sent to a remote AI service. • Use the interface in English, Russian, Korean, Japanese, or Chinese. Internet access is used for model downloads and optional model catalog and release searches. After a model is downloaded, chat generation works offline. On-device models can make mistakes and may have outdated information. Check important answers.