This Half-Gigabyte AI Model Runs Local Agents on Your Phone
In brief MiniCPM5-1B scores an average of 42.57 across agentic and reasoning benchmarks, beating the next-best 1B-class competitor’s 35.61. The model supports MCP and native...
Tag : Phone
This Open-Source Phone AI Agent Sees, Hears and Acts—All Without Touching the Cloud
In brief X-OmniClaw is an open-source Android AI agent from Oppo that keeps its core logic on-device and only calls the cloud for high-level reasoning....
Tether's Medical AI Runs on Your Phone and Outperforms Models 16x Its Size
In brief Tether’s 1.7 billion-parameter QVAC MedPsy outperformed Google’s MedGemma-4B and beat MedGemma-27B on HealthBench Hard, an OpenAI benchmark testing realistic clinical conversations graded by...