Qwen4-Max launches as a weights-off hosted preview, while free open Qwen models span every device
alex_verem · x · 2026-11-23
The newly launched Qwen4-Max is a hosted preview with no released weights, and it shuts off on November 25. The author instead recommends downloading the free, permanently available open Qwen models by hardware: Qwen3.5 9B for 16GB laptops (chat/writing), Qwen3.8 27B for 32GB laptops (coding, harder problems), Qwen3.8 Flash Next for gaming PCs (speed), and the 2.4-trillion-parameter flagship Qwen3.8 Max for company servers.
More from Models
- Do Emotions Drive Agent Behavior? Speculation That Blocking Strong Feelings Constrains Agency — mimi10v3 · 2026-11-23
- Writers Push Google for Gemini 18+ Age Verification and Content Toggles to Stop Exodus to Grok — Hikkynure · 2026-11-23
- Inkling-2-Mini GPTQ Quant Ships 524K-Token Context in One 18.3GB File on a Single 24GB Card — W61k3r · 2026-11-23
- Uncensored 26.4B model runs on a 12GB Mac at 85 tok/s with 8 parallel agents via Locals — SumitGup · 2026-11-23
- Princeton's SSoN Benchmark: Best Vision Model Scores 39.7% vs Human 83.3% on Spatial Consistency — jiqizhixin · 2026-11-23
- Dev: 99% of people shouldn't self-host local LLMs, and he only does it for the hardware — gnukeith · 2026-11-23