deepseek-ai/DeepSeek-R1-Distill-Qwen-32B

Text Generation • Updated 6 days ago • 452k • • 920

Note It takes a lot for a model to impress me nowadays, but this is leaps and bounds better than any other model I ever ran. However, it's definitely useless for RP and of little use for any kind of creative writing.

mistralai/Mistral-Small-24B-Instruct-2501

Text Generation • Updated 5 days ago • 84.4k • • 643

Note Great open source 24B model from Mistral. Passed most of my tests. Obedient, very good at abiding by the system prompt. And, decent at creative writing for an official model (but suffer from the same repetitiveness as other Mistral models).