Qwen 3.8 runs locally for 1.7 hours to generate AI daily news
Teknium · x · 2026-08-16
A user ran Qwen 3.8 (27B) locally on a Mac Mini with 24GB RAM as the top orchestrator within the Hermes Agent framework. The agent successfully aggregated the last 24 hours of AI news and generated a voice-over in a specific style, taking approximately 1 hour and 42 minutes. Benchmark speeds were around 16.8 tokens/sec for generation and 40.6 tokens/sec for prompt evaluation. The user plans to migrate the task to an RTX-5090 setup for significantly faster performance.
More from coding & agent
- Agent sprawl: managing 100 AI agents may be harder than cloud resources — Ok_Intention1336 · 2026-08-16
- Developer: 90% of AI agents are gimmicks; shares 3 workflows that actually made clients money — Affectionate-Ask7235 · 2026-08-16
- Developer Building UI/UX Plugins for DeepSeek Harness — op7418 · 2026-08-16
- Building a tool to catch AI agent regressions: developer seeks workflow insights — digbickindividual · 2026-08-16
- soul.md: A Portable Format for Defining Agent Personality — amu4biz · 2026-08-16
- WebOSINT: Automate Passive Domain Intelligence Gathering Script — tom_doerr · 2026-08-16