Qwen 3.8 27B on my laptop can interpret model weights, too

Re:Qwen 3.8 27B on my laptop can interpret model weights, too by simonw on Tuesday November 03, 2026 @03:22PM (#50357649)

Apparently Qwen 4 might land this week, and it uses the same architecture as 3.8-Flash-Next (so various LLM serving tools should be able to handle it already). I'm hoping Qwen 4 includes some smaller models - the last 4B and 9B from Qwen were for 3.5.

[ Parent | on HN ]

Re:Qwen 3.8 27B on my laptop can interpret model weights, too by fastball on Wednesday November 04, 2026 @02:18AM (#50362374)

[delayed]

[ Parent | on HN ]

Re:Qwen 3.8 27B on my laptop can interpret model weights, too by sigmoid10 on Wednesday November 04, 2026 @02:39AM (#50362482)

The head of Qwen just confirmed that 4 and 5 will remain open.

[ Parent | on HN ]

Re:Qwen 3.8 27B on my laptop can interpret model weights, too by NewJazz on Wednesday November 04, 2026 @11:28PM (#50375191)

[delayed]

[ Parent | on HN ]

Re:Qwen 3.8 27B on my laptop can interpret model weights, too by tancop on Thursday November 05, 2026 @03:30AM (#50376647)

Doesn't matter for local use anyway.

[ Parent | on HN ]

Re:Qwen 3.8 27B on my laptop can interpret model weights, too by boomskats on Wednesday November 04, 2026 @05:23AM (#50363551)

I remember seeing somewhere credible that it was going to be Thursday this week (tomorrow?), but don't remember where.

Assume you've seen the Apsara conf announcement / the planned 'tiers'[0]. Do you have a planned use case for a 4b / 9b? Hopefully the overthinking will get better on the smaller models.

[0]: https://www.yottalabs.ai/post/qwen-4-max-vs-plus-vs-flash-vs...

[ Parent | on HN ]

Re:Qwen 3.8 27B on my laptop can interpret model weights, too by ch_sm on Wednesday November 04, 2026 @02:17PM (#50370244)

I’m really wishing for a 35b-a3b version. It’s just such a great speed-capability trade off.

[ Parent | on HN ]