Jun Kim
@jundotkim
Open-Source ML Engineer at 🤗 Hugging Face | Creator of oMLX | I build the tools I wish existed for my Mac, then open-source them. junkim.dot@gmail.com
加入 February 2026
190 正在關注 3.7K 粉絲
always happy to see oMLX doing real work on long-horizon tasks. thanks @hxiao, for running it and posting the numbers!
people are sleeping on this release. I finally got a chance to test it today: qwen3.8-flash-next-q4 now runs at 50-70 tps on long-horizon tasks on M3 ultra, with no regression in quality or thinking. It used to be 20-30 tps. Very impressive work!
顯示更多
