d1-2B by Liquid AI :Same model, three engines on a MacBook Pro M5 Max
@ivanfioravanti45K followers
17,801 views
37 Comments
Comments from the original post on X (Twitter)

@ivanfioravanti
@starkov100 has the solution for the ANE usage from camera!!!
4 likes

@ivanfioravanti
@anemll can you try this on your Mac Mini M6 🙏 I'm curious to see results from new ANE!
4 likes

@ivanfioravanti
New release data are slightly different 🤷🏻♂️ ⚡ MLX: 88 ms, 65 W ⚡ Core AI GPU: 78 ms, 68 W 🔋 Core AI Neural Engine: 183 ms, 37 W
3 likes

@christopherowen
@liquidai super cool!
2 likes

@ivanfioravanti
@liquidai I'm creating the live deck of Local AI wonders! After this demo there is LFM3 to showcase differences!

@christopherowen
@liquidai I cannot wait to see it! the 7 wonders of the modern world!
1 like

@lucataco
@liquidai d1-2B isnt the same as d1.2 right?
2 likes

@ivanfioravanti
@liquidai It’s the previous, previous version.

@scottmillerio
@liquidai The camera bumping ANE usage is the detail I didn't expect. If the Neural Engine is shared with system features, a background model on it competes with the OS for time. Curious how steady that 197 ms stays with FaceTime or Continuity Camera running.
1 like

@ivanfioravanti
@liquidai We have solution!

@kcwolfy_
@liquidai Thank you for being the first person to actually focus on the speed of a decision, one open source model versus just the result. Because between one second and three seconds for a great result misses the point. 👏 @liquidai and @ivanfioravanti
1 like

@ivanfioravanti
@liquidai Thanks KC and thanks Liquid AI! Amazing model!

@hitakayoshikawa
Great comparison. For always-on workloads like voice dictation, that 37 W matters more than the extra 130 ms. I'm building Alice, a local Japanese dictation app on Apple silicon — curious whether the ANE gap shrinks for small STT encoders. Planning to test it on my M3 Ultra 512GB.
1 like

@lotar_vk
@liquidai Wait... Camera uses ANE 👀? I mean awesome model and test, but camera confused me extremely 😅 Also ANE might be slower but if this is fast enough it uses 1/3 of energy which is awesome (and not slow at all)!
1 like

@ivanfioravanti
@liquidai Not in this case, because I loaded a prerecorded video to avoid the problem. If you use live camera yes, it's using ANE and you'll get worst performance.
1 like

@lotar_vk
Yeah, I figured it's a recording. Really got me confused. Now I somehow think Apple is silently tracking everything camera sees (what would be any sensible reason for it to fire up - guessing not video processing with all of the CPUs and GPUs). Tin foil hat on, time to figure it out 😂

@alexdolbun
@liquidai Interesting direction, still not this 3ms decision like guys below 👇 done, but super impressive Mr. @ivanfioravanti GJ !! Reposted.
1 like

@ivanfioravanti
@liquidai But they did it with text not video 😎 This is why I like d1!
1 like

@Nklockiewicz
@liquidai Can't wait for the iPhone numbers, on a phone a quarter of the power is probably worth more than the 3x 👀

@ajshpprd
@liquidai For something that just sits there watching all day I'd take the slow lane at 37W every time. Speed only matters when someone's waiting on it














