My Mac Studio M3 Ultra has an identity problem. It thinks it's an M5.
@volatilemarkts2.6K followers
16,901 views
13 Comments
Comments from the original post on X (Twitter)

@landontgreen
TensorFold has me so excited for the future. It's such a big improvement and it's only the beginning!
9 likes

@arthurlee
What does this for M5?
2 likes

@volatilemarkts
Hopeful to have everyone numbers soon.
1 like

@HumanHitsSend
How much VRAM you got on that bird?
2 likes

@jodorowsk1
Oh, is the model quantized to 4 bits?
1 like

@niklaslenz_ai
How is this even possible?! One dude is literally changing local AI in realtime.
1 like

@AIQuanting
The 0.08 s first token is the cache doing the work. Cold runs are the number I'd want to see.

@ankushnarula
How well does it perform as context window scales up?

@spark_arena
Have you tried initial context above 32k and 2 or more concurrent requests?

@minviable_org
which weights ?

@lessaxwrong
Wow

@CowboyCoderHQ
I love tensorfold as much as the next dev, but don’t you think this comparison is a tad unfair. Why not show omlx with mtp and apc on vs tensorfold for a fair engine to engine comparison.

@AmirFromZH
Same quantization?
