BotPsy: On-Device Personal Assistant with a Sub-Billion-Parameter

Summary

Back to Articles a]:hidden"> BotPsy: On-Device Personal Assistant with a Sub-Billion-Parameter Agentic Language Model Team Article Published November 11, 2026 Upvote 1 Milan Gritta milangritta Follow qvac Jihye Back happy-jihye Follow qvac JinUk, Cho jucho2725 Follow qvac ohjoon kwon joooon Follow qvac Patrik Lambert patrik-lambert Follow qvac Mathias Buus mafintosh Follow qvac Amril Nurman Nurman Follow qvac:last-child]:mb-0"> Frontier cloud LLMs carry high operational costs that can fluctuate unexpectedly, and relying on such third-party models introduces vulnerabilities, as providers can modify, deny, or deprecate access at any time. Furthermore, proprietary models offer limited customization for specific workflows, while posing risks to privacy, data control, and transparency. Besides, not every task demands frontier-level intelligence: small, specialized agents can be equally capable on specific tasks and significantly cheaper to run, since many routine or smaller workloads can be processed efficiently on-device. As intelligence per parameter continues to improve rapidly, we aim to stand at the forefront of this shift toward performant, privacy-focused, self-hosted models.