This is the fastest local AI I've tried, and it's not even close - how to get it
SMRTR summary
Ollama's gpt-oss:20b model offers remarkably fast local AI processing at 30 tokens per second (120 characters/second), significantly outpacing alternatives like llama3.2. Users can install this 13GB model by updating Ollama to version 0.11.4+ and running "ollama pull gpt-oss:20b" from the command line, then access it through either CLI or GUI interfaces.
SMRTR provides this summary for quick context. The original article belongs to ZDNet.
Read the original article