DeepSeek V4.1 Flash. FREE plan.
$20 in monthly usage included 👀 How to try DeepSeek and Qwen in Perch without a paid subscription Perch lists DeepSeek V4.1 Flash on its free Starter plan. Qwen 3.8 Max is also included until November 20, 2026 at 10 PM PKT. No credit card
通过 DeepSeek Harness 运行的 Qwen 3.8 27B 模型制作的小镇看起来也挺不错的啊！
特别是光影效果，远近镜头切换，感觉能打啊！ 总花费也才211k token，而且全程在本地完成. 感谢@loktar00 给我们带来的测试！
Another side by side comparison of Qwen 3.8 Max vs. QoDuck (presumably some Qwen 4.0 variation).
Both using the same prompt and thinking level. Qwen 3.8 Max took 1 hour and 55 minutes with 137 iterations in one shot. QoDuck took 29 minutes and 30 seconds with 99 iterations in
Qwen 3.8 27b NVFP4 inside TensorFold native CLI on Windows 11 cooking on a nvidia RTX 5090.
🤯 Single-stream decode was ~220 tps for prose. Prefill was ~12,200 tps C=4 was over 500 tps decode. Will be in the next engine release 👌🏼
You have reached the end of the archive
All of qwen38