I'd love to see a tokens per second metric. I always prioritize speed over raw intelligence for flash models.

▲ throwaw12 6 hours ago | parent [-]

> I always prioritize speed over raw intelligence for flash models.

This model might have a perfect speed:

    for i in range(100):
      print(random.choices(words))

	▲	OsrsNeedsf2P 5 hours ago \| parent [-]
		Leave it long enough, and it'll print the work of Shakespear!