Locallama vs LLMster

This app is built around a simple idea: bring a real local small-model AI experience to your phone. Instead of relying entirely on cloud processing, it lets you run AI on-device whenever possible, so conversations, imported content, and everyday usage can stay closer to your own device. It is designed for people who care about privacy, offline access, and the practicality of having a personal AI companion in their pocket. Key features: Local inference, with stronger privacy by design AI processing is designed to happen on your phone whenever possible, reducing the need to send your content to remote servers by default. This makes it a better fit for personal notes, drafts, ideas, and other privacy-sensitive content. A real mobile small-model experience Open the app and interact directly with on-device AI. It offers a fast, lightweight, and more personal way to explore what small models can do on a phone. Import OpenClaw workspaces Bring in your OpenClaw workspace so your existing content, structure, and workflows can travel with you. It is a practical way to continue using your workspace in a mobile, local-first environment. Offline availability Many core experiences remain useful without a stable connection, making the app convenient for commuting, travel, or low-connectivity situations. Personal, device-first AI Your models, content, and workflows stay closer to your own device, helping you build a more personal and controllable AI setup. Simple mobile workflow Made for quick questions, lightweight writing, note capture, browsing workspace content, and everyday AI interactions on the go. Important limitations: This app focuses on the real experience of local small models, not on overstating their capabilities. Because the models run locally and are relatively small: reasoning depth is more limited than large cloud models answers may be less accurate, less complete, or less stable on complex tasks long, highly technical, or multi-step requests may not perform as well performance depends on your device, including speed, memory, and thermal limits If you need the strongest possible reasoning, broad knowledge coverage, or consistently high performance on demanding tasks, large cloud models are still a better fit. But if you value privacy, offline use, local control, and the feeling of having AI truly running on your phone, this app offers a distinctive and practical alternative.

LLMster is a fast, private iPhone and iPad client for models running on your LM Studio server (https://lmstudio.ai). Stream replies, reasoning, tool activity, and image-based conversations from the models you host—in an app designed to feel at home on iOS. Private by design LLMster connects directly to the server you choose. There’s no LLMster account, telemetry, hosted chat service, or cloud relay in the middle. Your conversation library stays on your device, while model context stays with your configured server. External integrations run only when you choose to enable them. Your models, wherever you run them Keep your models on the machine built for them: a workstation, home server, or always-on computer. Run the LM Studio desktop app or LM Studio’s headless daemon, point LLMster at the host, and start chatting. No companion desktop client is required. Choose the right model without leaving the conversation: • Search or sort by name, size, or format, then pin favorites • See which models support vision, reasoning, or tool calls • Change models without starting a new chat Organized from the start Search chats by title, model, or folder. Browse recent conversations across every folder, then organize, rename, pin, or duplicate important threads. Move and protect your chats Share individual conversations as .llmster files and import them on another device while preserving messages, images, reasoning, tool history, and chat settings. Back up and restore your entire local chat library—including folders, pins, drafts, and attachments—with optional password protection. Backups do not include server addresses, authentication keys, or app-wide settings. LLMster also verifies transferred response context against your configured LM Studio server before continuing a chat. Vision, direct to your server Attach up to four screenshots, photos, or scanned pages to a message and send them to a compatible vision model. LLMster resizes and compresses images on your device before sending them, so the originals remain with you. Open any attachment and pinch to zoom when you need to inspect the details. Hands-free voice chat Talk naturally using on-device speech recognition and text-to-speech. Audio stays on your device; only the resulting text is sent to your configured server. Natural turn-taking and subtle haptics keep the conversation moving without touching the screen. Control each conversation Every chat can have its own: • Integrations already configured in LM Studio • Custom system prompt • Tool-call visibility • Live reasoning preference Stream reasoning as Markdown while the model works, or keep the interface quiet with a compact Thinking indicator and open the completed reasoning when you want it. Control response auto-scrolling, and choose System, Light, or Dark appearance with your preferred accent color. Rich responses, as they arrive LLMster renders streaming Markdown smoothly, including syntax-highlighted code with copy controls, inline and block math, tables, links, lists, and more. Export or share transcripts with their original Markdown intact. Keep going while you move on Run LM Studio on a workstation or headless server and connect from your phone. With Tailscale on both devices, you can keep chatting over cellular or another Wi-Fi network while your models run at home. Setup instructions are available at https://llmster.app/support