Qwen 3.8 27b made this flight sim on my AMD Strix Halo this morning ✨✨
I used my own coding harness Marshall. I ran this prompt before and none of my much larger local models were able to achieve this, even in multiple turns. This new model rocks 👑
Qwen 3.8 puts an open 27B multimodal model on your own machine — and more
20 hours later and I’m done!
Qwen 3.8 27B @ 73 TPS (peak) on a Macbook pro M5 max. MTPLX V2.7 out now with 3 new models. - Bare Speed: short burst decode, good for chat. - Optimized Speed: higher quality and faster on long coding. - Optimized Quality: 30% slower but super!
Yep, it did it, one prompt 'ish, first created the game, 2nd fixed a hang and made player smaller
3rd was play the game and make a video, it created a bot, played and recorded via playwright, 4th convert the produced webm file to mp4, QWEN 3.8 is exceptional.
You have reached the end of the archive
All of qwen38