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
- Agents turn conservative as context grows: edits shrink from 150 to 30 lines — dbreunig · 2026-10-16
- ai& becomes an official built-in Cline provider with 13 open-weight models — DavidBennett__ · 2026-10-16
- Open-source rizin-mcp lets LLMs run local binary and malware analysis via Rizin — Pure_Emergency1424 · 2026-10-16
- x402 as a free GTM channel: agents discover 100+ tools, no API keys needed — 0xJeff · 2026-10-16
- Sam Altman: stop getting better at prompts, build loops and graphs that prompt for you — goyalshaliniuk · 2026-10-16
- POV ski game on real Matterhorn elevation data, built with Claude Opus 5.5 — techartist_ · 2026-10-16