[tarruda]

The official Q4_K_S gguf is quite good and has very good 35 tps generation on a M1 mac studio. Should be much faster on recent Macs, especially M5.

[SilverElfin]

What’s “Q4_K_S gguf” and where do I get it? Is it easy to install and configure on a MacBook?

[throw1234567891]

https://huggingface.co/stepfun-ai/Step-3.7-Flash-GGUF and you can use ollama: https://docs.ollama.com/import#Importing-a-GGUF-based-model-...