
Zach Nagengast
@zachnagengast
Followers
688
Following
4K
Media
110
Statuses
569
founding engineer @argmaxinc 🛠️ optimizing large models for the edge 📲⌚️💻🥽
Los Angeles, CA
Joined November 2011
RT @xeophon_: OH MY FUCKING GOD . I LOVE YOU @nvidia FOR THIS MODEL.I LOVE YOU @argmaxinc FOR THE IMPL.I LOVE YOU @jordibruin FOR THE APP….
0
6
0
RT @argmaxinc: Nvidia Parakeet v3 is out! Enjoy Day 0 support with Argmax SDK. - What changed from v2?.- How do I use it?.- Should I upgrad….
0
12
0
Really excited about this, local servers have emerged as the one-size-fits-all interface for on-device inference because they can simply match established API specs and point to localhost instead. At Argmax, we focus on optimizing the inference pipeline for the chip it's running.
Introducing Argmax Local Server. Run our state-of-the-art real-time transcription server directly on Mac!. 0:31 Feature complete for AI Meeting Notes apps.0:49 Migrate from cloud APIs with 1 line of code.1:05 Fastest speech models with top accuracy.1:31 Other apps do not slow
1
3
20
RT @awnihannun: Super intelligence in your pocket will happen. And if you want to accelerate the timeline hit me up. We’re working on this….
0
24
0
RT @argmaxinc: Major update to Argmax Pro SDK dropped today!.- Real-time transcription API now supports multiple concurrent sessions.- Diar….
0
8
0
RT @argmaxinc: Nvidia Parakeet v2 is slowly dethroning Whisper. @karpathy's vibecoding voice interface @superwhisperapp is now running Nvid….
0
12
0
RT @argmaxinc: The flagship @pyannoteAI speaker diarization model is now on Argmax SDK!. We are thrilled to bring the most accurate speaker….
0
12
0
RT @pyannoteAI: Where conversations happen, speaker intelligence should follow. pyannoteAI is now available on-device, thanks to our partne….
0
4
0
RT @jordibruin: MacWhisper now supports Nvidia's Parakeet models. 🏆 Second highest accuracy on the leaderboards.🚀 Up to 300x realtime spee….
0
43
0
1000+ tok/s easily achievable on modern macs as well with our VAD-based concurrency algorithm🏃♂️💨 ANE is great for this kind of model.
Nvidia Parakeet v2 running on M1 MacBook Air at 150 speed factor!. This is the slowest that frontier speech-to-text is and will ever be on device with Argmax, already faster than most cloud APIs.
0
0
20
RT @argmaxinc: During WWDC25, @Apple modernized its on-device speech recognition framework with the new SpeechAnalyzer. Many of you asked….
0
18
0
Nvidia model running on Apple Neural Engine 🤯 Excited to ship this - turns out the model is faster and more accurate than a lot of cloud transcription APIs today, and we got it running locally on an iPhone 📲 @NVIDIAAI cooked!.
Nvidia Frontier Speech Models on Argmax SDK.Nvidia's top-ranking speech-to-text models are now seamlessly running on device with Argmax SDK, available today!. Details in thread
6
6
73
RT @angeloskath: Kudos to David Koski! From discussion to merged PR in 2 days. You can't beat open source!.
0
3
0
RT @ClementDelangue: Everyone is talking about how we need more AI data centers (especially the ones who would mostly benefit from them) bu….
0
214
0