HuggingFace转发推文称,llama.cpp增加MTP支持后,Qwen3.6-27B密集生成模型在本地运行速度足够作为日常使用。推文获122点赞、12转发、11回复、9051次浏览。
RT @ClementDelangue: llama.cpp with MTP support makes local models fast enough to use as daily drivers 🚀
Qwen3.6-27B dense generation bel…
likes: 122 | retweets: 12 | replies: 11 | views: 9051