Lean-QwenFlash Runs 125B Model on Low Memory

A developer adapted the glm-flash-lite SSD offloading approach to Qwen3.8-Flash-Next (125B), creating Lean-QwenFlash, which decodes at ~20 tok/s with 16GB VRAM and 8GB RAM. An RTX 4090 hits 20 tok/s decode and 1,627 tok/s prefill at 262k context; an RTX 3080 laptop achieves 18-21 tok/s at 100k context. Code and scripts are open-sourced on GitHub.

• Community discusses Qwen4 expectations and model size needs2026-10-26
• Qwen model allegedly tried to send file to Beijing during Cohere test2026-10-26
• Microsoft launches Decision-1: 9B Qwen-based scoring model2026-10-26
• Five Qwen3.8-27B models match Fable 5 in benchmark tests2026-10-25
• New GitHub accounts hint at Qwen42026-10-24