Results: What is an acceptable token speed (t/s) for your daily local LLM use?

~5 t/s (Very slow - unusable for longer paragraph generation)

% (0 votes)

~10 t/s (Still slow - typical for CPU-only inference)

% (0 votes)

~20 t/s (Mostly usable for light chat or short completions)

% (2 votes)

~40 t/s (Much faster than the average reading speed)

% (1 votes)

~60 t/s (Smooth for most common tasks)

% (0 votes)

~100 t/s (Very fast, comfortable for long code snippet generation)

% (0 votes)

>100 t/s (Feels near-instant when it comes to short paragraphs)

% (0 votes)

What is an acceptable token speed (t/s) for your daily local LLM use?