Video wird geladen...

Video konnte nicht geladen werden

Zur Startseite

Day 1: Benchmarks We ran 1000+ LLM benchmarks on real consumer devices. Data includes single-device and multi-device clusters with Tokens-Per-Second (TPS) and Time-To-First-Token (TTFT). Setups tested: 3x M4 Mac Mini cluster, iPhone 15 + S24, RTX4090 & more.

exolabs's profile picture

EXO Labs

50,741 subscribers

254,968 Aufrufe • vor 1 Jahr •via X (Twitter)

Nachrichten & PolitikWissenschaft & TechnologieBildung
LIVE

Anya Rossi• Live Now

Private livecam show

0 Kommentare

Keine Kommentare verfügbar

Kommentare vom Original-Post werden hier angezeigt

Ähnliche Videos

M4 Mac Mini AI Cluster Uses EXO Labs with Thunderbolt 5 interconnect (80Gbps) to run LLMs distributed across 4 M4 Pro Mac Minis. The cluster is small (iPhone for reference). It’s running Nemotron 70B at 8 tok/sec and scales to Llama 405B (benchmarks soon).
0:19

M4 Mac Mini AI Cluster Uses EXO Labs with Thunderbolt 5 interconnect (80Gbps) to run LLMs distributed across 4 M4 Pro Mac Minis. The cluster is small (iPhone for reference). It’s running Nemotron 70B at 8 tok/sec and scales to Llama 405B (benchmarks soon).

Alex Cheema

3,516,469 Aufrufe • vor 1 Jahr

M4 Mac Mini AI cluster running Llama 3.3 70B Preliminary results show Gigabit ethernet switch (4 tok/sec) is slower than Thunderbolt-5 with EXO Labs Benchmarks including Thunderbolt-5 coming soonTM.
0:11

M4 Mac Mini AI cluster running Llama 3.3 70B Preliminary results show Gigabit ethernet switch (4 tok/sec) is slower than Thunderbolt-5 with EXO Labs Benchmarks including Thunderbolt-5 coming soonTM.

Alex Cheema

73,090 Aufrufe • vor 1 Jahr

Distributed training on M4 Mac Mini cluster We implemented Google DeepMind DiLoCo on Apple Silicon to train large models with 100-1000x less bandwidth compared to DDP baseline. AI is entering a new era where a distributed network of consumer devices can train large models.
0:16

Distributed training on M4 Mac Mini cluster We implemented Google DeepMind DiLoCo on Apple Silicon to train large models with 100-1000x less bandwidth compared to DDP baseline. AI is entering a new era where a distributed network of consumer devices can train large models.

EXO Labs

347,697 Aufrufe • vor 1 Jahr

m4 mac mini cluster with 5 nodes running exo
0:13

m4 mac mini cluster with 5 nodes running exo

Alex Ziskind

362,753 Aufrufe • vor 1 Jahr

What if your cloud agents could use iOS and Android devices just like that? Introducing Agent Device Cloud: hosted on your dusted Mac Mini, used through 𝚊𝚐𝚎𝚗𝚝-𝚍𝚎𝚟𝚒𝚌𝚎
0:12

What if your cloud agents could use iOS and Android devices just like that? Introducing Agent Device Cloud: hosted on your dusted Mac Mini, used through 𝚊𝚐𝚎𝚗𝚝-𝚍𝚎𝚟𝚒𝚌𝚎

Michał Pierzchała

13,351 Aufrufe • vor 3 Monaten

Introducing Find the best local models based on real data 1. People run and submit benchmarks 2. Stats aggregated over models / devices 3. Find the best model for you `npx whatcanirun`, fully open-source
0:16

Introducing Find the best local models based on real data 1. People run and submit benchmarks 2. Stats aggregated over models / devices 3. Find the best model for you `npx whatcanirun`, fully open-source

⁵⁄₉

133,401 Aufrufe • vor 3 Monaten

This is not possible with chatgpt… Only possible with an on-device LLM: - Real-time note monitoring - Adjusts difficulty in real-time - Announces progress
0:12

This is not possible with chatgpt… Only possible with an on-device LLM: - Real-time note monitoring - Adjusts difficulty in real-time - Announces progress

Adam Lyttle

60,311 Aufrufe • vor 10 Monaten

Another demo of the iPhone 17 Pro’s on-device LLM performance This time with Ling mini 2.0 by InclusionAI, a 16B MoE model with 1.4B active parameters running at ~120tk/s Thanks to Awni Hannun for the MLX DWQ 2-bit quants
0:11

Another demo of the iPhone 17 Pro’s on-device LLM performance This time with Ling mini 2.0 by InclusionAI, a 16B MoE model with 1.4B active parameters running at ~120tk/s Thanks to Awni Hannun for the MLX DWQ 2-bit quants

Adrien Grondin

46,205 Aufrufe • vor 9 Monaten

Introducing Nomic Embed - the first fully open long context text embedder to beat OpenAI - Open source, open weights, open data - Beats OpenAI text-embeding-3-small and Ada on short and long context benchmarks - Day 1 integrations with @langchain, Llama-index, MongoDB
0:10

Introducing Nomic Embed - the first fully open long context text embedder to beat OpenAI - Open source, open weights, open data - Beats OpenAI text-embeding-3-small and Ada on short and long context benchmarks - Day 1 integrations with @langchain, Llama-index, MongoDB

CalCo

369,317 Aufrufe • vor 2 Jahren

Multi-chain data, streamed in real-time. Get live prices, onchain trades & OHLCV data for 20M+ tokens with the CoinGecko WebSocket API.
0:12

Multi-chain data, streamed in real-time. Get live prices, onchain trades & OHLCV data for 20M+ tokens with the CoinGecko WebSocket API.

CoinGecko

1,325,514 Aufrufe • vor 7 Monaten

No matter where you go, and no matter which device, we believe your internet should go with you 🌏 Starting today, your Arc tabs, folders, & spaces SYNC in real-time across iPhone (Arc Search), Mac, & Windows. Android in the works. Here’s a demo from the new Arc Search app:
0:16

No matter where you go, and no matter which device, we believe your internet should go with you 🌏 Starting today, your Arc tabs, folders, & spaces SYNC in real-time across iPhone (Arc Search), Mac, & Windows. Android in the works. Here’s a demo from the new Arc Search app:

Josh Miller

53,257 Aufrufe • vor 2 Jahren

Just dropped on HF — NeuTTS Air Next-gen on-device TTS that matches cloud-level quality while staying fully open source. > Real-time speech synthesis on CPU/GPU > 3-second voice cloning, no cloud or data upload > Compact: under 200 MB, runs on mobile and edge devices > Multilingual and expressive > Developed by Neuphonic , optimized for speed and fidelity
0:13

Just dropped on HF — NeuTTS Air Next-gen on-device TTS that matches cloud-level quality while staying fully open source. > Real-time speech synthesis on CPU/GPU > 3-second voice cloning, no cloud or data upload > Compact: under 200 MB, runs on mobile and edge devices > Multilingual and expressive > Developed by Neuphonic , optimized for speed and fidelity

steven

72,273 Aufrufe • vor 9 Monaten

Wow, Apple finally catches up with Android here. Device Hub lets you control a connected iPhone directly from your Mac without constantly reaching for the device
0:14

Wow, Apple finally catches up with Android here. Device Hub lets you control a connected iPhone directly from your Mac without constantly reaching for the device

Hieu Dinh

363,026 Aufrufe • vor 28 Tagen

The Expansion of LayerAI Network with laiOS 🧬 Each laiOS device requires at least 1 token per device to operate. There are over 1 trillion devices in the world already. This number grows by tens of billions every year. If just 0.3% of devices opt into the network, that’s a demand for 3 billion $LAI. LayerAI aims to present the first working version of this product by Q1-Q2 of this year.
0:13

The Expansion of LayerAI Network with laiOS 🧬 Each laiOS device requires at least 1 token per device to operate. There are over 1 trillion devices in the world already. This number grows by tens of billions every year. If just 0.3% of devices opt into the network, that’s a demand for 3 billion $LAI. LayerAI aims to present the first working version of this product by Q1-Q2 of this year.

LayerAI | AI2Earn

22,949 Aufrufe • vor 1 Jahr

A startup in China packed roughly 1,000 Mac Mini M4 computers into a single data center to run AI workloads without paying ongoing cloud fees. The base Mac Mini M4 starts at $599 and draws just 10 to 30 watts under load, a fraction of the 300 to 500 watts a traditional GPU server pulls.
0:13

A startup in China packed roughly 1,000 Mac Mini M4 computers into a single data center to run AI workloads without paying ongoing cloud fees. The base Mac Mini M4 starts at $599 and draws just 10 to 30 watts under load, a fraction of the 300 to 500 watts a traditional GPU server pulls.

Massimo

1,888,376 Aufrufe • vor 23 Stunden

Running multiple accounts on one device was never supposed to work at scale. Yet professionals do it every day without bans, flags, or leaks. Octo Browser is the reason. A next-gen anti-detect infrastructure built to replicate real devices, secure data, and manage hundreds of accounts seamlessly. Multi-accounting isn’t the risk anymore; weak tools are. 👇
0:17

Running multiple accounts on one device was never supposed to work at scale. Yet professionals do it every day without bans, flags, or leaks. Octo Browser is the reason. A next-gen anti-detect infrastructure built to replicate real devices, secure data, and manage hundreds of accounts seamlessly. Multi-accounting isn’t the risk anymore; weak tools are. 👇

Alif Hossain

12,148 Aufrufe • vor 2 Monaten

CRYPTIC ALPHA V1 IS NOW LIVE After months of focused development and rigorous testing, Cryptic Alpha V1 is officially live on Android. This marks the first time quantum-safe messaging and private token swaps are delivered together in a single, consumer-grade mobile app protected by device-level encryption and built for real-world use. For the first time, privacy at this scale is accessible to everyday users. New integrations, features, and expansions are already underway as we continue building the future of private digital life.
0:10

CRYPTIC ALPHA V1 IS NOW LIVE After months of focused development and rigorous testing, Cryptic Alpha V1 is officially live on Android. This marks the first time quantum-safe messaging and private token swaps are delivered together in a single, consumer-grade mobile app protected by device-level encryption and built for real-world use. For the first time, privacy at this scale is accessible to everyday users. New integrations, features, and expansions are already underway as we continue building the future of private digital life.

Cryptic

21,336 Aufrufe • vor 6 Monaten

Track new token launches in real-time on mobile ⚡ → Discover newly launched, migrating, and migrated tokens → Monitor live data on holder count, market cap, and volume
0:15

Track new token launches in real-time on mobile ⚡ → Discover newly launched, migrating, and migrated tokens → Monitor live data on holder count, market cap, and volume

Phantom

168,034 Aufrufe • vor 9 Monaten

Demo of 1-bit Bonsai 8B from PrismML running on-device on iPhone 17 Pro More than 40tk/s for a dense 8B model on iPhone, that’s a first Powered by Apple MLX and available now in Locally AI
0:15

Demo of 1-bit Bonsai 8B from PrismML running on-device on iPhone 17 Pro More than 40tk/s for a dense 8B model on iPhone, that’s a first Powered by Apple MLX and available now in Locally AI

Adrien Grondin

159,914 Aufrufe • vor 3 Monaten