24pointsSwift-Qwen3.8-27BPost-trained Qwen 3.8-27B for faster, shorter thinkingShow HN · 9 comments · 11 h agoSwift-Qwen3.8-27B
104votesSwift-Qwen3.8-27BPost-trained Qwen 3.8 27B that cuts thinking length and speeds inference; research API.Product Hunt · 3 comments · 18 h agoSwift-Qwen3.8-27B