Bro… someone just built in one shot a Mario clone locally with Qwen 3.8 27b

Link:

Joman 👺Sep 21

Gemini 3.8 Flash High effort Vs Qwen 3.8 27B Max effort

BenSep 2

A 125B MoE model Just hit 25 tokens/sec on a single RTX 4090 at home.

Qwen 3.8 Flash Next + MTP speculative decoding at - 80k context. - 25.35 t/s decode - 471 t/s prefill Running a 125B Mixture-of-Experts model on a single consumer GPU

Md Ismail Šojal 🕷️Sep 22

Took 15 minutes to make this with Qwen 3.8 27B locally running on my RTX Laptop and serving to my Macbook .

Welcome to the Real World , MATRIX!!!

Spunky MonkeySep 22