I like [mistral-nemo](https://ollama.com/library/mistral-nemo) "A state-of-the-art 12B model with 128k context length, built by Mistral AI in collaboration with NVIDIA."

Nada to be honest. I keep trying every new model, and invariably go back to llama 8b.

Llama8b is the new mistral.

Qwen 2.5 has just released, with a surprising amount of sizes. The 14B and 32B look pretty promising for their size class but it's hard to tell yet.

I like the latest qwen2.5 (https://nexaai.com/Qwen/Qwen2.5-0.5B-Instruct/gguf-q4_0/read...). It was just released last week. It is one of the best small langauge models right now according to benchmarks. And it is small and fast!

codestral 22b, aya-23 35b, gemma2 27b-instruct.