Qwen/Qwen3.5-27B

Image-Text-to-Text • 28B • Updated 21 days ago • 1.52M • • 705

Note 2026's flavor of Qwen. Excellent for serious stuff, as usual. Plus at 28B, you can fit the vision layer without having to kill too much context or quantizing too hard. The thinking block tends to be massive, though.

zai-org/GLM-4.7-Flash

Text Generation • Updated Jan 29 • 1.76M • • 1.61k

Note Damn it's fast and clever. I'm generally not a fan of MoE models, but this one is really, really, good. It will however eat a bazillion tokens in its thinking block.

zerofata/MS3.2-PaintedFantasy-v4.1-24B

24B • Updated 27 days ago • 175 • 10

Note First RP model of the year in this list. Similar to previous iterations, but grounded by normal assistant prompts. It's a really solid model, fun to use, adaptable beyond RP too. It uses L7-Tekken as an instruct format. Supports thinking mode optionally.