The #1 local AI platform built on Apple Silicon. Try Nativ: https://nitter.cf/t.co/PDIjDai0Ca
Joined August 2026
- Tweets176
- Following13
- Followers1K
- Likes134
Your bug report. Your model request. Your 2am PR. That's how Nativ gets better.
We believe AI should run locally, on your own Mac, and belong to you. In the future we want that for everyone. With your help, we'll get there.
What should we build next? 👀
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.
runnativ.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 💻
runnativ.ai
Github repo 🛠
github.com/Blaizzy/nativ
Not sure which one to grab? Go 4-bit. It matched BF16 word for word on all three clips, ran 1.7× quicker, and tops out around 20 GB instead of 66.
Congrats to @liquidai on LFM3! Now in Nativ 🎉
Text, vision, audio and omni, all around 2B · fully on-device.
Ask your Mac something out loud with the Wi-Fi off, and it usually answers out loud in under a second.
On an M5 Max at 4-bit:
🎙️ an hour of audio turned into text in about a minute
👀 Omni answers a question about a photo in 0.15 s
🎬 and about a short clip in half a second
💾 under 3.3 GB at peak
Liquid's first omni model, and nothing you say leaves your Mac.
Download for macOS 💻
runnativ.ai
Collections 💪
huggingface.co/collections/L…
Github repo 🛠
github.com/Blaizzy/nativ
Then the reply streams in faster than you can read it: about 290 tokens a second on both, and still around 170 deep into a 128K-token chat.
The text and vision models are in too. Paste in a long report and it's read in seconds: on an M3 Ultra, LFM3-1.7B takes in about 7,000 tokens a second, and LFM3-VL-2B keeps pace the whole way.
Omni sees as well as hears. Snap a photo, ask about it out loud, and it answers out loud in under 2 seconds. Type the question instead and the answer's back in 0.15 s. What would you point it at first?
That lecture recording you never got around to typing up? Both models turn speech into text 52 to 65× faster than real time. Talking back is quick too: a 10-second answer is ready in about a second.
Congrats to @OpenBMB on MiniCPM-OCR! Now in Nativ 🎉
OCR 1.0 (1.3B) reads the page in Nativ. Jev (2B), its fact-checker, runs on your Mac too and flags the lines worth a second look.
On an M5 Max in full BF16:
🧾 an invoice read in 0.38 s
📄 a packed full page in under 3 s
🎯 each read checked in about 63 ms
Still retyping totals off scanned invoices? Drop the page in and it's text before you've found the first number, and the scan never leaves your Mac.
Download for macOS 💻
runnativ.ai
Github repo 🛠
github.com/Blaizzy/nativ
Tiny invoice or a page crammed edge to edge, you'd think the busy one would slow it down. It doesn't. The text streams back at 220 to 235 tokens a second on every page we tried, way faster than you can read it.
Nativ retweeted
"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:
neywalabs.ai/blog/docling-ml…
Nativ retweeted
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.
neywalabs.ai/
Flint and Phonon now run in Nativ. Local coding + on-device voice, all on your Mac 📷
Nativ v0.4.3:
→ Recursive Flint: 40B MoE, day 0 on Apple Silicon
→ Gradium Phonon TTS: 4 voices, first audio under 15 ms
→ New Phonon deep dive on the blog
→ Smoother model picker
→ Snappier chat sidebar
→ Free local AI. Nothing leaves your Mac
Try Nativ: blaizzy.github.io/nativ
Congrats to @Recursive_SI on Recursive Flint! Day 0 support in Nativ 📷
40B MoE · 2.5B active · 256K context · fully on-device.
On an M3 Ultra in full BF16:
⚡️ 2,641 tok/s prefill · 51 tok/s decode
🚀 Batch 8 lifts decode to 236 tok/s
📏 Still 33 tok/s decode at 128K
🔓Open weights under Apache 2.0
A 40B coding model that never sends your code anywhere.
Download for macOS 📷
blaizzy.github.io/nativ/
Long context holds up. Decode goes from 51.3 tok/s at 1K to 32.7 tok/s at 128K, and prefill peaks at 2,641 tok/s at 4K. Single request, M3 Ultra, BF16.
