DeepSeek R1 671B running on 2 M2 Ultras faster than reading speed
1–10 of 32 posts
Re: DeepSeek R1 671B running on 2 M2 Ultras faster than reading speed
#2[flagged]
Re: DeepSeek R1 671B running on 2 M2 Ultras faster than reading speed
#3[flagged]
That's a hell of a lot cheaper than running the equivalent H100 at home...
And cheaper than a lot hobbyists' bicycles!
Re: DeepSeek R1 671B running on 2 M2 Ultras faster than reading speed
#4Please note that it’s using pretty aggressive quantization (around 4 bits per weight)
Re: DeepSeek R1 671B running on 2 M2 Ultras faster than reading speed
#5[flagged]
That's a hell of a lot cheaper than running the equivalent H100 at home... And cheaper than a lot hobbyists' bicycles!
And only twice as expensive as the competing hardware you use to run R1 671B at 3-bit quantization!
Ordinarily Apple customers cough up 3 or 4 times list price to match the performance of an equivalent PC. This is record-setting generosity from Cupertino.
Re: DeepSeek R1 671B running on 2 M2 Ultras faster than reading speed
#6[flagged]
It is a 671B params model, but I guess you already knew that from the title.
But you're right, just let's keep waiting for the town-sized Data Centers + Power Plants kindly served by our big tech overlords.
PS: If you refer to it being a Mac, obviously you can build a more cost efficient but difficult to cool rig.
Re: DeepSeek R1 671B running on 2 M2 Ultras faster than reading speed
#7[flagged]
There are lots of people with ATVs and hobby motorbikes etc. that cost a good bit more.
Re: DeepSeek R1 671B running on 2 M2 Ultras faster than reading speed
#8Please note that it’s using pretty aggressive quantization (around 4 bits per weight)
Its not that aggressive of a quantization considering that the full model was trained at only 8 bits.
Re: DeepSeek R1 671B running on 2 M2 Ultras faster than reading speed
#9Fascinating to read the thinking process of a flush vs a straight in poker. It's circular nonsense that is not at all grounded in reason — it's grounded in the factual memory of the rules of Poker, repeated over and over as it continues to doubt itself and double-check. What nonsense!
How many additional nuclear power plants will need to be built because even these incredibly technical achievements are, under the hood, morons? XD
Re: DeepSeek R1 671B running on 2 M2 Ultras faster than reading speed
#10[flagged]
14k in 2025 is about 6400 in 1992.