Sencha vs Hushfox

A native LLM client for on-device inference, LLM APIs, and self-hosted servers, built around a minimal, responsive interface. Download a supported model and chat offline without an API key or account. Or connect OpenRouter, direct providers, and compatible endpoints using your own credentials. On-Device Models • Download models from the built-in catalog, including Gemma 4, Qwen 3.5, Bonsai, and LFM 2.5 • Choose model sizes and quantization options to suit your device • Configure context window, reply length, and image detail where supported • Use streaming, thinking traces, image attachments, and web tools with compatible models • Reduce reprocessing of earlier messages with on-disk prompt caching Model capabilities and performance depend on the selected model and available device memory. Connections and Models • Connect OpenRouter, OpenCode, and direct providers • Add OpenAI- or Anthropic-compatible endpoints, including self-hosted runtimes such as Ollama and LM Studio • Use Chat Completions, Responses API, or Messages API • Choose an on-device or connected model per chat • Browse model catalogs and inspect context size, output limits, pricing, and capabilities where available • Configure reasoning effort, prompt caching, routing, and model tools where supported Web Search and Fetch • Use the included free web search via Markdown.new • Or configure Brave Search, Tavily, Exa, Serper, SerpApi, Parallel, or Keenable • Choose search-depth presets for Exa and Tavily • Fetch pages on device or through Markdown.new or Firecrawl • Configure fetch providers and fallbacks independently Files and Output • Attach photos, documents, and PDFs • Send PDFs natively, extract embedded text, run on-device OCR, or render pages as images • Read responses with formatted Markdown, code, mathematical formulas, and tables • Copy generated tables as a table, Markdown, or a complete image Voice Input • Use Apple Speech for on-device dictation • Download local transcription models • Connect API-based transcription providers The app is free, with no ads or app subscription. On-device models require no provider account or API key. Connected services are subject to their own pricing, limits, and data policies.

Hushfox runs language models entirely on your phone. Nothing you type leaves the device: there is no server that could receive it, no account to create, and no cloud to sync to. Download any GGUF model from Hugging Face and start chatting. You need a connection once, to fetch the model. After that it works fully offline, on a plane, on the subway, or anywhere with no signal. Private by design Your prompts and answers stay on the device. Hushfox has no analytics SDK and no hidden network calls. A built-in log shows you exactly what, if anything, leaves your phone. Any open model Bring any GGUF from Hugging Face. On iPhone and iPad you can also run MLX models. The only real limit is your device RAM: in practice, 3B to 8B models quantized to 4 bits run on a modern phone. Long conversations that stay put Pick up a long chat instantly. Context is kept on device, so a conversation you started days ago is right where you left it. Yours to control No subscription wall to open the app. No sign-in. No tracking. You choose the model, you keep the data. Frequently asked Does it work without internet? Yes. You only need a connection once, to download a model. What models does it support? Any GGUF from Hugging Face, plus MLX on iPhone and iPad, within the limit of your device RAM. Are my conversations sent anywhere? No. There is no server that can receive them.