google/gemma-4-31B-it

Image-Text-to-Text • 31B • Updated Jul 20 • 7.53M • • 4.3k

Note Excellent official model, after a very boring 2025 year, 2026 is shaping to be awesome. It's surprisingly compliant for a corporate model. It has some structural repetition issues, and it loves its em-dashes and slop sentences way too much, but this is definitely going to be very strong base for fine-tuners. Also, its SWA KV cache means that you can fit a lot more context in much less space that you'd normally need.

Qwen/Qwen3.8-27B

Image-Text-to-Text • 28B • Updated 1 day ago • 7.85M • • 19.3k

Note 2026's latest 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. Good KV cache use too, making it easy to work with longer context. The thinking block tends to be needlessly massive, as usual with Qwen models.

zai-org/GLM-4.7-Flash

Text Generation • 31B • Updated Jan 29 • 1M • • 1.9k

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. It is very bad at writing, and quite censored.

zerofata/G4-LuneLight-31B

31B • Updated 12 days ago • 415 • 31

Note Good RP / creative model based on Gemma 4. Thinking and tool-calls work out of the box. Less sloppy delivery than most of other fine-tunes, and it doesn't do that G4 thing of going for longer and longer responses over time.

Nimbz/Zwielicht-27B

28B • Updated Sep 6 • 1.37k • 13

Note Very decent uncensored merge of various creative Qwen 3.8 models. Thinking and tool-calls are correctly preserved. It tends to be quite wordy, but on the other hand, the thinking block isn't as massive as with default Qwen, so it's about the same.

zerofata/Q3.5-BlueStar-v2-27B

27B • Updated Mar 20 • 41 • 47

Note Creative model based on Qwen 3.5. Thinking and tool-calls are preserved (but model needs to be given orders). Strong contender for a mixed use case. Decent job, but still early. v3 is shaping to be a lot better.

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

24B • Updated Feb 19 • 201 • 22

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.