GLM 5.3 on 8 x RTX Blackwell 6000's @ 120 tok/s with OMP.
No skills. No plugins. Local Qwen 3.8 27B for vision 👀 Great at making neat little things to look at, like this ship in a bottle! One-shot prompt below 👇
HY4 preview vs Glm 5.3 vs Qwen 3.8 max
ZML/LLMD running Qwen 3.8 27B w16a16 at 13250 tok/s on 4xGB300
Qwen 3.8 is the best AI model to run on your computer.
I'll show you how to install it with Command: ollama run qwen3.8:27b-mlx Then try it and let me know in the comments how it goes.
You have reached the end of the archive
All of qwen38