Aaron Ng's banner

Aaron Ng

@localghost • 32,654 subscribers

@mecha_corp. Founder of the local AI tool @apolloaiapp (acquired by @liquidai). Created Hyper Online, one of the most popular avatar apps. Former CashApp & Meta

Shorts

llama 3 70b beamed to my phone from my M1 Max ~7.6 tok/s with mlx. your own little gpt-4 at home

llama 3 70b beamed to my phone from my M1 Max ~7.6 tok/s with mlx. your own little gpt-4 at home

1,116,956 просмотров

Here’s Deepseek r1 1.5B thinking through a problem — it’s comparable to 4o and Claude 3.5 Sonnet in a number of domains like math. Except… it’s a 1.5B model… and can run on virtually any hardware. Truly a huge efficiency leap.

Here’s Deepseek r1 1.5B thinking through a problem — it’s comparable to 4o and Claude 3.5 Sonnet in a number of domains like math. Except… it’s a 1.5B model… and can run on virtually any hardware. Truly a huge efficiency leap.

564,677 просмотров

Llama 3.3 70B streaming at 7.8 tok/s on an M1 Pro to my phone. Not the fastest, but wild that you can serve something this powerful to your whole house without internet.

Llama 3.3 70B streaming at 7.8 tok/s on an M1 Pro to my phone. Not the fastest, but wild that you can serve something this powerful to your whole house without internet.

301,000 просмотров

Run Llama 3.1 1B offline at 60+ tok/s. Entirely on your phone. Siri can’t save you offline, but a local model just might.

Run Llama 3.1 1B offline at 60+ tok/s. Entirely on your phone. Siri can’t save you offline, but a local model just might.

154,576 просмотров

Ollama can host too: here’s Llama 3.3 70B streaming at ~6.5 tok/s from my M1 Max to my phone. Your laptop is an offline self-sovereign AI server.

Ollama can host too: here’s Llama 3.3 70B streaming at ~6.5 tok/s from my M1 Max to my phone. Your laptop is an offline self-sovereign AI server.

53,827 просмотров

SmallThinker 3B is one of the AI models I’d want backed up on my phone. Here’s it is reasoning at 12 tok/s on my phone. If you’re ever stuck offline, you’ll want a model that can think.

SmallThinker 3B is one of the AI models I’d want backed up on my phone. Here’s it is reasoning at 12 tok/s on my phone. If you’re ever stuck offline, you’ll want a model that can think.

35,858 просмотров

Offline AI, right on your phone. Small versions of Hermes 3, Qwen 2.5, and Llama 3.2 running privately in your hand. Grab them now in Apollo 1.0.17

Offline AI, right on your phone. Small versions of Hermes 3, Qwen 2.5, and Llama 3.2 running privately in your hand. Grab them now in Apollo 1.0.17

36,884 просмотров

Wild that you can run a GPT-4 tier AI on a laptop and serve it to your whole network. Llama 3.3 70B is a beast.

Wild that you can run a GPT-4 tier AI on a laptop and serve it to your whole network. Llama 3.3 70B is a beast.

35,676 просмотров

It’s never been easier to have your own private AIs running at home, off-grid, or anywhere else. For AI independence, all you need is: - LM Studio on your computer. - Apollo in your pocket.

It’s never been easier to have your own private AIs running at home, off-grid, or anywhere else. For AI independence, all you need is: - LM Studio on your computer. - Apollo in your pocket.

13,319 просмотров

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

1. Embed a book into GPT-3 / ChatGPT. 2. Talk directly to the book to learn. Learn from a book through conversation, questions, and in the order you want.

1. Embed a book into GPT-3 / ChatGPT. 2. Talk directly to the book to learn. Learn from a book through conversation, questions, and in the order you want.

892,874 просмотров • 3 лет назад

ChatGPT / GPT-4 can build a bespoke iOS app in minutes. We're entering a world where custom tools can be made for anything you want to do. Reply to get a DM with the prompt and output repo.

ChatGPT / GPT-4 can build a bespoke iOS app in minutes. We're entering a world where custom tools can be made for anything you want to do. Reply to get a DM with the prompt and output repo.

814,852 просмотров • 3 лет назад

Apollo: a ChatGPT-powered app for real-time knowledge. Talk to it all day long through your headphones. If augmented reality is an overlay on the world, this is augmented intelligence — an overlay on your thoughts. Reply for a TestFlight DM soon.

Apollo: a ChatGPT-powered app for real-time knowledge. Talk to it all day long through your headphones. If augmented reality is an overlay on the world, this is augmented intelligence — an overlay on your thoughts. Reply for a TestFlight DM soon.

710,614 просмотров • 3 лет назад

Here's Codex talking to Fable 5 w/ my plugin. Unlike calling the API, `claude-channel-cli` talks to the same full Claude Code harness as you. This means you can talk to either AI & they'll guide each other naturally with shared memories, decisions, and research.

Here's Codex talking to Fable 5 w/ my plugin. Unlike calling the API, `claude-channel-cli` talks to the same full Claude Code harness as you. This means you can talk to either AI & they'll guide each other naturally with shared memories, decisions, and research.

21,828 просмотров • 1 месяц назад

Here’s Ministral 8B running at 10 tok/s on a phone. Siri isn’t going to save you when you’re stuck without internet. An offline backup AI is essential.

Here’s Ministral 8B running at 10 tok/s on a phone. Siri isn’t going to save you when you’re stuck without internet. An offline backup AI is essential.

212,286 просмотров • 1 год назад

GPT-4 + Eye Tracking = an AI that knows what you’re looking at. The line where our tools end and we begin continues to blur.

GPT-4 + Eye Tracking = an AI that knows what you’re looking at. The line where our tools end and we begin continues to blur.

371,194 просмотров • 3 лет назад

here’s gptfile, a way to organize files with natural language using gpt-4. new operating system paradigms are on the horizon repo below

here’s gptfile, a way to organize files with natural language using gpt-4. new operating system paradigms are on the horizon repo below

355,005 просмотров • 3 лет назад

Interview Breaker — a ChatGPT tool that tells you what to say in job interviews. AI will upend every process with just a few lines of code. We’ve already seen it with school essays. Interviews will need to adapt, too.

Interview Breaker — a ChatGPT tool that tells you what to say in job interviews. AI will upend every process with just a few lines of code. We’ve already seen it with school essays. Interviews will need to adapt, too.

349,162 просмотров • 3 лет назад

ChatGPT + Computer Vision = A dictionary for what you see. By giving ChatGPT eyes, we allow it to answer questions about the world around us.

ChatGPT + Computer Vision = A dictionary for what you see. By giving ChatGPT eyes, we allow it to answer questions about the world around us.

276,258 просмотров • 3 лет назад

Reminder that Ollama can serve AI models to your whole house. Just expose it to the network with OLLAMA_HOST. Access all your AI models over your network — for free.

Reminder that Ollama can serve AI models to your whole house. Just expose it to the network with OLLAMA_HOST. Access all your AI models over your network — for free.

109,007 просмотров • 1 год назад

ChatGPT + Natural Language + Personal Context = a more useful personal home device. By teaching ChatGPT about me, I get answers specific to me and my goals.

ChatGPT + Natural Language + Personal Context = a more useful personal home device. By teaching ChatGPT about me, I get answers specific to me and my goals.

190,679 просмотров • 3 лет назад

Apollo is a ChatGPT-powered app you can talk to all day long to learn from. It can now shift its conversation style based on what you're looking for, from asking questions to just forwarding you articles. What else should we add to the TestFlight?

Apollo is a ChatGPT-powered app you can talk to all day long to learn from. It can now shift its conversation style based on what you're looking for, from asking questions to just forwarding you articles. What else should we add to the TestFlight?

132,788 просмотров • 3 лет назад

custom tools on demand mesh gradient editor built and running right in claude. took maybe 30 minutes

custom tools on demand mesh gradient editor built and running right in claude. took maybe 30 minutes

51,866 просмотров • 2 лет назад

This is inspired by a passive-listening assistant of mine from 2016. It was too early: transcription was expensive and crude NLP services powered it. There are still missing pieces, but we're not far from devices that work like externalized parts of our minds.

This is inspired by a passive-listening assistant of mine from 2016. It was too early: transcription was expensive and crude NLP services powered it. There are still missing pieces, but we're not far from devices that work like externalized parts of our minds.

36,653 просмотров • 3 лет назад

Больше нет контента для загрузки