Qwen 3.8 27B + TensorFold built a game for my Hardball 3D challenge in 3h 14m.

Of the three builds, it’s the most playable, even more so than the GPT-6 Luna baseline. Decode · 90th percentile: 42.37 tok/s Prefill · mean: 160.55 tok/s Run details:

Alfredo Artiles 🇨🇺Oct 52

Paris Nocturne - by Qwen 3.8 Flash Next at 3bpw no thinking loop no break one shot prompt 3 hour working...

This complexity, the thinking process almost same as intelligent with Opus 5.5 or Fable 5.. look at the shading sky, the horizon, the baloon, ferrieswheel, the river, the

lackonendesOct 54

【AIニュース】2026年10月5日 早朝トップニュース ・Run Qwen 3.8 Flash Next (125B) on consumer hardware (RTX 4090) at 100T/s

カエル｜AIに全部やらせる経営者Oct 4

Went on vacation this weekend.

While I was gone, I had Qwen 3.8 Flash Next run through 125 hours of long form content and generate 779 clips. 🥶🫣👌 My clipping & affiliate side gigs have been nonstop consistent the past 4–5 months. Ai schedule posts on 2 sets of 6 different

CryptoBanditOct 4