- Added LFM 3 (1.7B) for on-device writing, summaries, reasoning, and everyday questions. - Added LFM 3 VL (2B) for understanding photos, documents, and charts, with support for up to four images per message. - Added the ability to move chats into Projects directly from the chat actions menu. - Updated chat actions with a compact list for Stream Responses, Use Memory, Voice Mode, and supported reasoning controls. - Improved sidebar navigation—tap the visible chat page to close the sidebar, or swipe back as usual.

Whats New - Explore more local models, including Bonsai 2, MiniCPM-V 4.7, and new LFM 2.5 options. - Attach up to four photos with supported vision models to compare images and ask follow-up questions. - See response speed in tokens per second and tap to compare it with your recent average, with an option to hide it in Settings. - Enjoy smoother scrolling, message sending, and keyboard transitions. - Keep typing after stopping a reply without the keyboard unexpectedly closing. - Remove photo attachments individually and see clearer image limits for your selected model. - Fixed UX/UI Bugs

What’s New in 2.0.0 - Refreshed UX/UI experience. - Organize your work with Projects, bringing chats, shared instructions, and reference files together. - Create personal Assistants with custom instructions, private knowledge, and dedicated conversation histories. - Connect your iPhone to your Mac with OS Bridge to use your Mac’s models and access shared workspaces. - Explore new local models with more choices for everyday conversations, reasoning, and image understanding. - Get started on Mac with redesigned onboarding, device checks, and model downloads built into setup. - Configure Web Search with your preferred supported provider. - Benefit from improved file handling, clearer download errors, and better recovery when OS Bridge disconnects.

**What’s New in 1.2026.05** - Improved iOS chat reliability when using web search and image attachments. - Fixed cases where local MLX models could stop before generating a response. - Added clearer fallback messages when a generation stops unexpectedly. - Improved streaming stability so completed responses are preserved more reliably. - Reduced jarring scroll movement when sending messages in existing conversations. - Restored Ministral 3 model availability in the model catalog. - Added an in-app What’s New screen for release highlights. - Updated the app version shown in Settings to `1.2026.05`.

What’s New * Run code directly with Artifacts for a more capable workspace. * Added Real-Time Web Search, powered by Oscilla’s private search engine. * Revamped Reasoning so you can better follow how supported models think through complex prompts. * Added Reasoning for Gemma 4 (E2B) * Added new local models with improved options for speed, intelligence, and on-device use. * Nvidia Nemotron Mini 4B * IBM Granite 4.1 (3B & 8B) * LFM 2.5 (350M, 1.2B Instruct, 450M VL) * OpenBMB MiniCPM-V 4.6 * Improved onboarding and model selection for devices that need local model downloads. * Improved web citations so sources are cleaner and easier to open. * Improved Streaming Run Time * Fixed Storage Bug * Fixed Bugs * Improved UX/UI

What’s New * Run code directly with Artifacts for a more capable workspace. * Added Real-Time Web Search, powered by Oscilla’s private search engine. * Revamped Reasoning so you can better follow how supported models think through complex prompts. * Added Reasoning for Gemma 4 (E2B) * Added new local models with improved options for speed, intelligence, and on-device use. * Nvidia Nemotron Mini 4B * IBM Granite 4.1 (3B & 8B) * LFM 2.5 (350M, 1.2B Instruct, 450M VL) * OpenBMB MiniCPM-V 4.6 * Improved onboarding and model selection for devices that need local model downloads. * Improved web citations so sources are cleaner and easier to open. * Improved Streaming Run Time * Fixed Storage Bug * Fixed Bugs * Improved UX/UI

This update improves local reasoning models, vision handling, and the chat experience across Oscilla. - Fixed reasoning support for Qwen 3 and Qwen 3.5, including cleaner thinking controls, better parsing, and safer defaults. - Added proper thinking support for SmolLM3 and LFM 2.5 Thinking. - Added Gemma 4 reasoning support with model-specific thinking behavior. - Reasoning is now opt-in by default for supported models, and always disabled in Voice Mode. - Removed reasoning and Voice Mode controls from LFM 2.5 Thinking where they do not apply. - Improved the reasoning UI with a cleaner Working, Thinking, and Analyzing state. - Added new reasoning UX/UI. - Improved image routing for Qwen 3.5 so text and vision paths are handled more safely. - Added safeguards for Qwen 3.5 vision on lower-memory devices. - Improved chat scroll behavior when sending messages and rerunning responses.