News for hackers. Stuff that matters.

A comment on Qwen 3.8 27B on my laptop can interpret model weights, too. Parent comment

Re:Qwen 3.8 27B on my laptop can interpret model weights, too by beachsidebunnie on Tuesday November 03, 2026 @04:01PM (#50358131)
The context window left on my 24GB card with Gemma is to low to do any major task though. Maybe small diffs or a single direct task. But Qwen has enough context for agentic tasks.
[ Parent | on HN ]
Re:Qwen 3.8 27B on my laptop can interpret model weights, too by ActorNightly on Tuesday November 03, 2026 @10:13PM (#50361122)
32k context on my 3090 runs fine.
[ Parent | on HN ]
Re:Qwen 3.8 27B on my laptop can interpret model weights, too by DavidSchor on Wednesday November 04, 2026 @07:04AM (#50364432)
32k context is quite limited in agentic context. Qwen 3.8 27b is much better in agentic and coding workflows. Gemma4 31b is much better in general assistant and language focused workflows.
[ Parent | on HN ]