ChatQLM vs Pipette by Liquid

ChatQLM - Your Quantum-AI Optimization Companion Unlock the power of quantum-inspired and classical optimization right from your mobile device. ChatQLM lets you describe real-world problems in natural language, and delivers optimized solutions using a smart hybrid stack of AI reasoning and advanced solvers - no technical expertise required. Why ChatQLM? • Speak your problem naturally - tell ChatQLM what you want to optimize, schedule, or plan. • Automatic solver choice - intelligent selection between classical, quantum-inspired, and real quantum compute. •⁠ ⁠Results with explanations - understandable outcomes, not black-box numbers. •⁠ ⁠Credit-based compute model - flexible usage without surprise costs. • Mobile-first and intuitive design - optimized for on-the-go productivity. Features •⁠ ⁠Solve optimization challenges like scheduling, routing, allocation, and resource planning. •⁠ ⁠Use a mix of AI + classical + quantum annealing or gate-based hardware behind the scenes. •⁠ ⁠Get recommendations & insights instantly in chat form. How It Works ChatQLM’s smart AI parses your goal, extracts constraints and objectives, and routes your problem to the best solver available - from fast classical engines to cutting-edge quantum backends. You stay focused on your problem; ChatQLM handles the compute. Ideal For •⁠ ⁠Students & researchers exploring optimization models • Professionals solving logistics, planning, and scheduling problems • Curious minds looking to experience quantum compute today Beta Notice: ChatQLM is currently in an active beta release. While some core features are available, some functionality may be experimental, under development, or subject to change. Users may occasionally experience bugs, performance issues, or unexpected behavior as we continue to test, optimize, and expand the platform. We appreciate your feedback as it helps us improve stability, accuracy, and overall experience ahead of the full public release. Get started with ChatQLM and discover how advanced optimization can be simple, powerful, and accessible - all from your device. Terms of Use (EULA): https://www.apple.com/legal/internet-services/itunes/dev/stdeula/

How fast can your phone run real AI? Pipette is an on-device AI benchmark app. It runs small models on your phone and measures actual performance without cloud processing. See how quickly your device processes prompts and generates text, measured in tokens per second. Many mobile benchmarks estimate AI performance using synthetic tests. Pipette downloads real, openly available AI models and runs them locally with the inference engine built into the app. The result is a benchmark that reflects how an offline AI assistant, local chatbot, or other on-device AI application would actually perform on your phone. What you can do with Pipette • Run AI models on your phone • Benchmark prefill speed, generation speed, latency, and peak memory use • Test popular model families like Liquid, Qwen, Gemma, Llama, Granite, and Mistral • Compare model sizes and quantization levels such as Q4 and Q5 • See results in tokens per second with per-model breakdowns • Use thermal readiness checks for more consistent runs • Export benchmark results as CSV • Optionally contribute results to Liquid AI's public dataset • And more… Fair, repeatable results Device temperature can have a major effect on performance. Pipette includes a thermal readiness check that waits until your phone is cool enough before starting a benchmark. This helps produce more consistent results across devices and repeated runs. Who Pipette is for • Developers building local AI, offline AI, and on-device AI apps • Hardware enthusiasts comparing smartphones and chipsets • Reviewers who need a repeatable mobile AI benchmark • Researchers and community members who want to contribute to Liquid AI's benchmark database • Anyone curious about how well their phone can run AI locally How it works • Sign in with your email • Choose a benchmark and the context length • Download the AI model • Run the test and view your results AI model downloads may be several gigabytes. A Wi-Fi connection is recommended. Pipette is built by Liquid AI, creators of Liquid Foundation Models, efficient AI models designed for on-device inference.