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

Text Generation • Updated 13 days ago • 973k • • 1.14k

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 20 days ago • 729k • • 804

Note Great open source 24B model from Mistral. Passed most of my tests. Obedient, very good at abiding by the system prompt. But, a lot worse at creative writing than 22B, it suffers from the same repetitiveness as other Mistral models. It's more a task oriented LLM than a generalist one.

DavidAU/L3-Grand-Story-Darkness-MOE-4X8-24.9B-e32-GGUF

Text Generation • Updated 4 days ago • 6.86k • 12

Note I don't normally look at 'mixture of experts' models, but that might have been a mistake. This one is really impressive. It's good both in creative writing and assistant roles. It's very good at handling complex prompts, and its writing style is surprisingly natural.