Samuel Zeng's banner

Samuel Zeng

@SamuelZengML • 4,349 subscribers

Founder, https://t.co/rfLQ050cr0 | On-device foundation models. High intelligence, low memory, low power | MIT TR35 https://t.co/WQ9mrGQA21

Shorts

How does Edge0 run a 35B model with only 1–2.5 GB of peak memory? In simple terms: • The full model stays in storage. • Only the parameters needed for the current step are loaded into memory. • The next parameters are prepared while the current step is running. • Memory is reused instead of loading the entire model at once. Large model. Small working set. Fully on-device.

How does Edge0 run a 35B model with only 1–2.5 GB of peak memory? In simple terms: • The full model stays in storage. • Only the parameters needed for the current step are loaded into memory. • The next parameters are prepared while the current step is running. • Memory is reused instead of loading the entire model at once. Large model. Small working set. Fully on-device.

34,026 views

Videos

Anya Rossi

sweetdream.ai

SweetDream.ai•Sponsored•Livecam

Watch Anya Live

Anya is streaming live right now! Join her private show and enjoy exclusive content.

Exclusive private shows

1.2k viewers online

Private Show

Join now for exclusive access

Free preview available • Premium content

A 35B language model running on an iPhone using only 1–2.5 GB of peak memory. No cloud. No remote server. No desktop GPU. Today, we’re open-sourcing Edge0 — a framework for running large AI models fully on-device.

A 35B language model running on an iPhone using only 1–2.5 GB of peak memory. No cloud. No remote server. No desktop GPU. Today, we’re open-sourcing Edge0 — a framework for running large AI models fully on-device.

726,936 views • 1 month ago

Speech recognition is easy—until you ask it to listen forever. Today we’re open-sourcing Audio8 ASR Infinite: Ultra-low latency, unlimited audio, 24/7 transcription, no drift. Built-in semantic turn detection keeps it listening like a human ear. New SOTA for streaming ASR.

Speech recognition is easy—until you ask it to listen forever. Today we’re open-sourcing Audio8 ASR Infinite: Ultra-low latency, unlimited audio, 24/7 transcription, no drift. Built-in semantic turn detection keeps it listening like a human ear. New SOTA for streaming ASR.

166,867 views • 1 month ago

Three weeks ago, we released the first version of Edge0: “A 35B language model running on a local device, using only 1–2.5 GB of peak memory.” Today, we’re taking the next step. We’re open-sourcing the Edge0 app layer—now available on: 📱 iOS 🖥️ macOS 🤖 Android 🪟 Windows One app. Four platforms. Fully on-device.

Three weeks ago, we released the first version of Edge0: “A 35B language model running on a local device, using only 1–2.5 GB of peak memory.” Today, we’re taking the next step. We’re open-sourcing the Edge0 app layer—now available on: 📱 iOS 🖥️ macOS 🤖 Android 🪟 Windows One app. Four platforms. Fully on-device.

85,126 views • 28 days ago

Over the past two months, we’ve open-sourced multiple generations of on-device Audio models to the community through Audio8. The current portfolio includes: • ASR: 0.1B, 0.3B, 0.6B, and 3B • TTS: 0.1B, 0.3B, and 0.6B These releases are designed for practical local inference, with deployment targets spanning phones, PCs, and other resource-constrained devices.

Over the past two months, we’ve open-sourced multiple generations of on-device Audio models to the community through Audio8. The current portfolio includes: • ASR: 0.1B, 0.3B, 0.6B, and 3B • TTS: 0.1B, 0.3B, and 0.6B These releases are designed for practical local inference, with deployment targets spanning phones, PCs, and other resource-constrained devices.

89,382 views • 1 month ago

The world’s smallest Transformer-based TTS model? We’re open-sourcing Audio8 TTS Preview 0.1B — an approximately 170M-parameter multilingual speech model with zero-shot voice cloning that delivers surprisingly strong, cloud-level quality in a dramatically smaller footprint.

The world’s smallest Transformer-based TTS model? We’re open-sourcing Audio8 TTS Preview 0.1B — an approximately 170M-parameter multilingual speech model with zero-shot voice cloning that delivers surprisingly strong, cloud-level quality in a dramatically smaller footprint.

75,946 views • 2 months ago

What can you build with Edge0? Playable games, entirely on-device. Start with a natural-language idea. Edge0 can generate the game logic, write the code, and refine the result locally. Around 2 GB of peak memory. No cloud calls.

What can you build with Edge0? Playable games, entirely on-device. Start with a natural-language idea. Edge0 can generate the game logic, write the code, and refine the result locally. Around 2 GB of peak memory. No cloud calls.

24,757 views • 1 month ago

Interactive web experiences, generated on-device. Edge0 can turn natural-language requirements into frontend structure, logic, and interactions, then iterate on the result locally. From the first prototype to the final refinement, the workflow stays on-device.

Interactive web experiences, generated on-device. Edge0 can turn natural-language requirements into frontend structure, logic, and interactions, then iterate on the result locally. From the first prototype to the final refinement, the workflow stays on-device.

23,424 views • 1 month ago

3D scenes, built locally. Describe what you want in plain language. Edge0 can generate a structured 3D scene, then modify and refine it on your phone or PC. No project data leaves the device.

3D scenes, built locally. Describe what you want in plain language. Edge0 can generate a structured 3D scene, then modify and refine it on your phone or PC. No project data leaves the device.

21,642 views • 1 month ago

No more content to load