Blog
Written versions of our YouTube videos, so you can check the numbers and tables at your own pace.
-
Mac mini M6 AI Image: 3 min 20 s to 2 min 20 s, Qwen-Image 2.1 Measured (youtube.com)
On a Mac mini M6 32GB, Qwen-Image 2.1 took 3 min 20 s in default ComfyUI, about 2 min 20 s with just the model file switched to bf16, and about 2 min with mflux 4-bit. Korean text accuracy and memory picks included.
-
RTX PRO 6000 Slower Than the 4090? MiniMax H3 GPU Test (youtube.com)
We ran the same AI video on an RTX 3090, 4090, 5090 and PRO 6000. With int8 the 4090 was fastest, and the PRO 6000 won only with the original bf16. Speed, power and rental cost.