Qwen 3.8 flash next IQ3s voxel pagoda prompt.
5070ti + 80GB RAM. 3100 tok/s prefill, 70-80tok/s decode.
Booth is ready at AI Engineer Shanghai.
Heading to AI Engineer Shanghai (Nov 5-6)? I'll be at the Raytone booth. Two things for builders: 1. Every new signup gets 1 billion tokens free (GLM 5.3 / Qwen 3.8) 2. Startups: selected teams get a free Raytone AIBox (normally from
Tomorrow: AIE Shanghai. Raytone is a Gold sponsor at AI Engineer Shanghai, Nov 5-6.
Clone a UI against the clock, Star our open source repo. Win a limited numbered tee. Every signup at the Raytone booth gets 1 billion tokens (50,000 credits) for GLM 5.3 and Qwen 3.8. See you.
How to run Qwen 3.8 27B on your laptop for $0 💻
Why now: Simon Willison just had this 17GB open model read raw model weights (a test from an MIT paper). It got 3 of 4 games right. Apache-2.0, 8M downloads in 30 days. 1. Install LM Studio (free) and search "Qwen3.8-27B" 2.
You have reached the end of the archive
All of qwen38