YOU ARE VIEWING ONE ITEM FROM THE AICRIER FEED

Linger runs 125B agent on 12GB GPUs

AICrier tracks AI developer news across Product Hunt, GitHub, Hacker News, YouTube, X, arXiv, and more. This page keeps the article you opened front and center while giving you a path into the live feed.

// WHAT AICRIER DOES

7+

TRACKED FEEDS

24/7

SCRAPED FEED

Short summaries, external links, screenshots, relevance scoring, tags, and featured picks for AI builders.

Linger runs 125B agent on 12GB GPUs
OPEN LINK ↗
// 1h agoOPENSOURCE RELEASE

Linger runs 125B agent on 12GB GPUs

SimplexAI Labs released Linger, an open-source personal desktop agent that leverages PolyStrata's tiered MoE inference engine to run a 125B parameter model locally on 12GB consumer GPUs. It combines proactive background automation, cross-app integrations, and a self-updating local wiki memory system with zero API fees.

// ANALYSIS

Linger demonstrates that consumer-tier MoE offloading has matured from an inference curiosity into a viable foundation for private, always-on desktop agents. Bypassing cloud API tolls while running high-parameter reasoning locally shifts the personal assistant paradigm from hosted subscriptions to local sovereignty.

  • –Tri-tier memory offloading in PolyStrata keeps active router weights in VRAM while streaming dormant experts through system RAM and NVMe, achieving ~45 tokens per second on an RTX 3060.
  • –Nightly offline consolidation converts inboxes, calendars, and communications into a structured personal wiki graph, reaching 95% on the LoCoMo benchmark without bloating conversational context windows.
  • –Proactive background routines and recursive self-improvement loops allow the agent to monitor tasks and automate workflows locally without leaking telemetry.
  • –Zero local token overhead removes the recurring API costs that usually make continuous multi-agent background loops cost-prohibitive.
// TAGS
lingerpolystrataagentagent-memorymoelocal-firstopen-source

DISCOVERED

1h ago

2026-11-19

PUBLISHED

2h ago

2026-11-19

RELEVANCE

8/ 10

AUTHOR

0x0SojalSec