Qwen3.8 Max Preview is reportedly thinking for 10 to 30 minutes
vista8 · x · 2026-07-21
Users are reporting that Qwen3.8 Max Preview can think for an unusually long time before answering — in one case nearly 10 minutes for a single prompt, and another reportedly 30 minutes.
The model also tends to produce very long outputs, making it feel powerful but hard to use unless you are patient.
More from Models
- Apple-π benchmark asks whether video models reason about physical laws or just mimic motion — liuziwei7 · 2026-07-21
- A user wants a fully local desktop agent stack for file ops and small scripts — Tonka-Jahari-Pizza · 2026-07-21
- OpenAI models look best at drawing and understanding complex SVG diagrams — mimi10v3 · 2026-07-21
- Kimi K3 beats Fable 5 on a landing page prompt while costing $0.25 — socialwithaayan · 2026-07-21
- Models now make decent PPTX decks, and people are acting like that’s normal — ziv_ravid · 2026-07-21
- A joking post asks whether this was the famous “move 37” moment for math — NielsRogge · 2026-07-21