Search: on device
🇺🇸 United StatesGemini Robotics
A vision-language-action model from Google DeepMind built for robotsMultimodal · API only · 2025
🇺🇸 United StatesSiri AI
Apple's rebuilt Siri assistant, powered by Apple Foundation Models and Google GeminiAssistant · API only · 2026
🇺🇸 United StatesApple Intelligence
Apple's on-device and cloud AI features built into iOS, iPadOS and macOSGeneral · API only · 2024
🇺🇸 United StatesPhi
Microsoft's small open-weights language models that run on a single deviceSmall · Open weights · 2023
🇺🇸 United StatesGemini
Google DeepMind's multimodal LLM family, from Nano to UltraGeneral · API only · 2023
🇺🇸 United StatesGemma 4
Google DeepMind's open multimodal models in five sizes, from phones to serversGeneral · Open weights
🇺🇸 United StatesLlama 3.2
Small text models and vision models from Meta for edge devices and image tasksMultimodal · Open weights · 2024
🇺🇸 United StatesPhi-3
Small Microsoft language models built to run well on phones and laptops.Small · Open weights · 2024
🇺🇸 United StatesLFM2
Hybrid language models for edge and on-device useSmall · Open weights
🇺🇸 United StatesSmolLM2
Compact language models for on-device useGeneral · Open weights · 2025
🇮🇳 IndiaPragna-1B
Small decoder model for Hindi, Bangla, Gujarati and EnglishSmall · Open weights
🇫🇷 FranceMinistral 3B and 8B
Two small Mistral AI models built for on-device and edge computing.Small · API only · 2024
🇺🇸 United StatesPaLM 2
Google's multilingual Transformer language model in four sizes, from on-device to largestGeneral · API only · 2023
🇰🇷 South KoreaMi:dm 2.0
Korea-centric language model by KTGeneral · Open weights · 2025
🇺🇸 United StatesApple Foundation Models
Apple's on-device and server language models behind Apple IntelligenceGeneral · API only · 2024
🇺🇸 United StatesApple Foundation Models
Apple's 2025 on-device and server language models for Apple IntelligenceGeneral · API only · 2025
🇺🇸 United StatesGemma
Small open-weight language models from Google, in 2B and 7B sizesGeneral · Conditional licence · 2024
🇺🇸 United StatesGemma 3n
Mobile-first open model family for on-device text, image and audio workMultimodal · Open weights · 2025