News for hackers. Stuff that matters.
Re:Qwen 3.8 27B is excellent, but it defaults to overthinkin... by oblio on Monday August 17, 2026 @06:29AM (#49328790)
> transcribe or translate anything you say

Is it multimodal? How do you do transcription with it?

Re:Qwen 3.8 27B is excellent, but it defaults to overthinkin... by simonw on Monday August 17, 2026 @08:41AM (#49329901)
Gemma 4 E2B, E4B and 12B unified accept audio - here's a recipe using MLX that can use it for transcription: https://simonwillison.net/2026/Apr/12/mlx-audio/

Only up to 30s though, and the larger 26B A4B and 31B models are text and image only.

Re:Qwen 3.8 27B is excellent, but it defaults to overthinkin... by kroaton on Monday August 17, 2026 @01:41PM (#49334787)
Or you can use parlor to chat with it directly https://github.com/fikrikarim/parlor/