Edmilson Manjate

Creative Director, brand films, motion, design & Making offline AI look as good as it works.

[Edmilson Manjate @Ed_Manjate]

@RaminNasibov GPU

[Edmilson Manjate @Ed_Manjate]

@trenych 🫣

[Edmilson Manjate @Ed_Manjate]

@patrick_kuhnke_ Not a problem if its smart laziness 😏

[Edmilson Manjate @Ed_Manjate]

Another signal you should strongly consider owning your intelligence 🫵🏾

[Pubity @pubity]

OpenAI CEO Sam Altman believes people owning RAM is wasteful, and that it belongs in data centers instead.

"From a global allocation perspective, actually, it’s quite terrible to have everyone have a bunch of the world’s limited supply of DRAM sitting in their own computer."

[Edmilson Manjate @Ed_Manjate]

@Prince_Canuma Especially when the founder says yes to the weird ones, like an arcade game hidden on the company's site 👀

[Edmilson Manjate @Ed_Manjate]

With a great team you’ll never run out of ideas 💡

[Edmilson Manjate @Ed_Manjate]

@Prince_Canuma Yup, same. Voice dictation + browse use 🙌🏾🙌🏾🙌🏾

[Nativ @Nativ_AI]

Picking a MacBook is the fun part. Clicking through every option to order it isn't.

Type it once and Nativ does the clicking. It even spots that the touch screen you asked for isn't available.

Running locally on your Mac with @OpenBMB's MiniCPM-V 4.7.

https://t.co/Jt8JCtPOJM

[Edmilson Manjate @Ed_Manjate]

@trenych Count me in! I make a lot of benchmark cards for model launches, and I'd love to see those numbers move without opening AE. Can it take real data from a table?

[Nativ @Nativ_AI]

Congrats to @NVIDIAAI on Nemotron 3.5 Transcribe! Day 0 support in Nativ 🎉

40 languages · speaker labels · translation · fully on-device.

On an M3 Ultra at 4-bit:

⚡ a 54 s chat between two people, transcribed with speaker labels in 1.6 s
🚀 27 to 34× faster than real time
💾 about 20 GB at peak, under a third of BF16
🎯 the same transcript as BF16 on every clip we ran

Got a call you'd never upload anywhere? Drop the recording in and get back who said what, without it ever leaving your Mac.

Download for macOS 💻
https://t.co/PDIjDai0Ca

Github repo 🛠
https://t.co/tg3OzuBoST

[Edmilson Manjate @Ed_Manjate]

@VladSushchenko @Neywalabs Clear skies 🏞️

[Neywa Labs @Neywalabs]

"Every time we release a model, the first thing Mac developers ask for is an MLX version."

Peter Staar, @IBMResearch

So now Docling runs on mlx-vlm out of the box on any Apple Silicon Mac, 9.2x faster

pip install "docling[vlm]" mlx-vlm

Case study here:

https://t.co/brlkLOJuNp

[Edmilson Manjate @Ed_Manjate]

@ivanfioravanti @Prince_Canuma 🔥🔥🔥

[Edmilson Manjate @Ed_Manjate]

@JohnTierney_ @Prince_Canuma Great catch, thanks!

[Edmilson Manjate @Ed_Manjate]

@Chromadera @Prince_Canuma We're not training our own models. We built the engine that runs the best open ones on your own device. Try it in @Nativ_AI 🚀

[Prince Canuma @Prince_Canuma]

Today, a single AI agent can cost tens of thousands a month to run. That puts AI out of reach for most builders, and for the billions who still have no access at all.

Local AI changes that. The model runs on your own device, and your data never leaves it.

That's the era of sovereign AI.

[Edmilson Manjate @Ed_Manjate]

Neywa Labs is live 🚀

Every tool I love, I own. My camera, my lenses, my edit. They work wherever I am, and nobody can take them away.

AI should be the same. We believe offline AI is the future, and everyone should own their intelligence.

That's what we're building.

@Neywalabs

[Prince Canuma @Prince_Canuma]

Today we're coming out of stealth, introducing Neywa Labs 🚀

We built the infrastructure to build and deploy AI that runs on the devices people already own. Private, offline, unlimited.

One mission: make AI available to everyone in the world.

https://t.co/FhoDfAWjru

[Edmilson Manjate @Ed_Manjate]

👀👀

[Prince Canuma @Prince_Canuma]

Tomorrow is a huge day!

Something we've been building quietly for a while. Stay tuned, the 24h clock starts now 🚀

[Edmilson Manjate @Ed_Manjate]

@bvchidra Yup, you either evolve or stay bitter 🤷🏾‍♂️