inclusionAI/Ling-3.0-tiny

Text Generation • 8B • Updated 4 days ago • 19k • 492

Note Perfect for most non-agentic tasks, has almost completely replaced Gemma 4 12B + Qwen 3.5 9B for me.

google/gemma-4-12B-it

Any-to-Any • 12B • Updated Jul 20 • 1.93M • 1.62k

Note Perfect for writing or light agentic tasks, but a lot of things Ling will do just as good and way faster.

Qwen/Qwen3.8-27B

Image-Text-to-Text • 28B • Updated Aug 14 • 6.84M • • 16.5k

Note Handles agentic tasks amazingly and is a very capable general assistant. Still not good enough for any moderate-to-difficult coding without significant hand-holding, Ling 3.0 Flash or Qwen 3.8 Flash Next is probably the next smallest model that's genuinely good at code.