Video wird geladen...

Video konnte nicht geladen werden

Zur Startseite

Introducing IOTA Decide 4B, our first public model. Pareto optimal. Built different. Trained across globally distributed GPUs with our SDK. Open weights, Apache-2.0. 🤗

MacrocosmosAI's profile picture

Macrocosmos

7,725 subscribers

136,815 Aufrufe • vor 5 Tagen •via X (Twitter)

Wissenschaft & Technologie
LIVE

Anya Rossi• Live Now

Private livecam show

10 Kommentare

Profilbild von Macrocosmos
Macrocosmosvor 5 Tagen

78.6 on the JevBench composite -- balancing capability, calibration, speed and cost. Ranking top 10 of 300+ systems, open and closed, within 3 points of #1, despite having only 4B params.

Profilbild von Macrocosmos
Macrocosmosvor 5 Tagen

IOTA Decide 4B sits on the Pareto frontier: no smaller model scores higher. It's cheap to run. ~$0.0037 per 1,000 decisions self-hosted.

Profilbild von Macrocosmos
Macrocosmosvor 5 Tagen

Led by @v_truba based on Qwen3.5-4B and trained using ~879k decision examples. But built different: - Trained distributed, end to end, using streaming DiLoCo across 16 RTX A4000s. - Training data came from our own stack: we generated and labelled it with distributed batch inference.

Profilbild von Macrocosmos
Macrocosmosvor 5 Tagen

IOTA Decide 4B is our first open model, but it won't be our last. Build with us: 🌐

Profilbild von xTAO - a Bittensor company
xTAO - a Bittensor companyvor 5 Tagen

Good work, team IOTA 👏

Profilbild von SubConnect
SubConnectvor 5 Tagen

Pretty cool, congrats guys!

Profilbild von luis
luisvor 5 Tagen

@Presidentlin

Profilbild von 鼬
鼬vor 5 Tagen

a usable 4b out of globally distributed training is the actual news to me, the model itself is almost secondary

Profilbild von Landyn
Landynvor 4 Tagen

Just found this on the "Latest Market News" tab on coingecko as well. Pretty cool to see it there

Profilbild von Kryptonite
Kryptonitevor 5 Tagen

Amazing stuff!

Ähnliche Videos

Introducing 0GM-1.0-35B-A3B. Our first proprietary AI model. Mixture of Experts (MoE), 35B parameters, 3B active per token. Trained on our own decentralized GPU network. Open source under Apache 2.0.
0:31

Introducing 0GM-1.0-35B-A3B. Our first proprietary AI model. Mixture of Experts (MoE), 35B parameters, 3B active per token. Trained on our own decentralized GPU network. Open source under Apache 2.0.

0G Labs

48,940 Aufrufe • vor 5 Monaten

Introducing Cursor 2.0. Our first coding model and the best way to code with agents.
1:04

Introducing Cursor 2.0. Our first coding model and the best way to code with agents.

Cursor

3,573,127 Aufrufe • vor 1 Jahr

Introducing OpenDiLoCo, an open-source implementation and scaling of DeepMind’s Distributed Low-Communication (DiLoCo) method, enabling globally distributed AI model training.
0:21

Introducing OpenDiLoCo, an open-source implementation and scaling of DeepMind’s Distributed Low-Communication (DiLoCo) method, enabling globally distributed AI model training.

Prime Intellect

260,002 Aufrufe • vor 2 Jahren

Command A+ from Cohere is out now :) its our best model yet and its open source apache 2.0
1:55

Command A+ from Cohere is out now :) its our best model yet and its open source apache 2.0

Nick Frosst

205,361 Aufrufe • vor 5 Monaten

Today, we're introducing PlayHT2.0 - our new Conversational Text-to-Voice AI Model that's trained and built to generate humanlike conversations across languages with <1s latency. Sign up for beta access -
1:19

Today, we're introducing PlayHT2.0 - our new Conversational Text-to-Voice AI Model that's trained and built to generate humanlike conversations across languages with <1s latency. Sign up for beta access -

PlayAI

52,378 Aufrufe • vor 3 Jahren

Meet d3-ultra: our newest open 27B multimodal decision model. #2 of 230 on the Jev Decision Index text board, +3.03 over d3. Text, images, video: it boxes what it finds and tracks it through time. Open weights (Apache-2.0): #Jev #Decision
1:05

Meet d3-ultra: our newest open 27B multimodal decision model. #2 of 230 on the Jev Decision Index text board, +3.03 over d3. Text, images, video: it boxes what it finds and tracks it through time. Open weights (Apache-2.0): #Jev #Decision

Xunzhuo

12,534 Aufrufe • vor 13 Tagen

Meet Iris-3B: a pixel-space T2I model and general vision learner that generates every pixel directly. No VAE. Pre-trained from scratch, 3B, open weights. We also explore its generative prior on detail-critical vision tasks: depth estimation and image restoration. Fully open: weights, code and demo (Apache 2.0)
0:43

Meet Iris-3B: a pixel-space T2I model and general vision learner that generates every pixel directly. No VAE. Pre-trained from scratch, 3B, open weights. We also explore its generative prior on detail-critical vision tasks: depth estimation and image restoration. Fully open: weights, code and demo (Apache 2.0)

Speridlabs

109,958 Aufrufe • vor 1 Monat

Meet Idol, an open image-to-3D model. A 3D-DiT that generates complete 3D objects from just an image. Pre-trained from scratch, contains only 600M parameters, it runs on consumer GPUs, using less than 7.2 GB of VRAM and can generate 1M splats in 3 seconds. Try it today. Fully open: weights, code and demo (Apache 2.0)
0:44

Meet Idol, an open image-to-3D model. A 3D-DiT that generates complete 3D objects from just an image. Pre-trained from scratch, contains only 600M parameters, it runs on consumer GPUs, using less than 7.2 GB of VRAM and can generate 1M splats in 3 seconds. Try it today. Fully open: weights, code and demo (Apache 2.0)

Speridlabs

223,362 Aufrufe • vor 11 Tagen

Introducing Chroma Context-1, a 20B parameter search agent. > pushes the pareto frontier of agentic search > order of magnitude faster > order of magnitude cheaper > Apache 2.0, open-source
13:20

Introducing Chroma Context-1, a 20B parameter search agent. > pushes the pareto frontier of agentic search > order of magnitude faster > order of magnitude cheaper > Apache 2.0, open-source

Chroma

1,126,583 Aufrufe • vor 7 Monaten

Introducing Mochi 1 preview. A new SOTA in open-source video generation. Apache 2.0. magnet:?xt=urn:btih:441da1af7a16bcaa4f556964f8028d7113d21cbb&dn=weights&tr=udp://tracker.opentrackr.org:1337/announce
0:51

Introducing Mochi 1 preview. A new SOTA in open-source video generation. Apache 2.0. magnet:?xt=urn:btih:441da1af7a16bcaa4f556964f8028d7113d21cbb&dn=weights&tr=udp://tracker.opentrackr.org:1337/announce

Genmo

1,284,033 Aufrufe • vor 2 Jahren

1/5 🚀 Thrilled to open-source OSCAR 🤖 — an action-conditioned world model for robotics, led by the visiting student in my group Zhuoyuan Wu! It generalizes across different robot embodiments with precise action controllability. All trained on a single GH200 GPU, and outperforms existing open-sourced baselines, which have larger model capacity and need more compute. Everything is public, including training data. 📄 Paper: 🌐 Project: 💻 Code: 🤗 Robot data: 🤗 Human data: 🤗 Weights: #Robotics #WorldModels #AI #OpenSource
0:31

1/5 🚀 Thrilled to open-source OSCAR 🤖 — an action-conditioned world model for robotics, led by the visiting student in my group Zhuoyuan Wu! It generalizes across different robot embodiments with precise action controllability. All trained on a single GH200 GPU, and outperforms existing open-sourced baselines, which have larger model capacity and need more compute. Everything is public, including training data. 📄 Paper: 🌐 Project: 💻 Code: 🤗 Robot data: 🤗 Human data: 🤗 Weights: #Robotics #WorldModels #AI #OpenSource

Jun Gao

105,237 Aufrufe • vor 5 Monaten

Introducing GPT-Rosalind, our frontier reasoning model built to support research across biology, drug discovery, and translational medicine.
2:34

Introducing GPT-Rosalind, our frontier reasoning model built to support research across biology, drug discovery, and translational medicine.

OpenAI

2,357,394 Aufrufe • vor 6 Monaten

NEW: OpenAI releases Privacy Filter, their first open model of 2026! 🤗 Apache-2.0! It's a bidirectional token-classification adaptation of GPT-OSS, trained to mask personally identifiable information (PII) in text. At only 1.5B params, it can even run locally in your browser!
1:22

NEW: OpenAI releases Privacy Filter, their first open model of 2026! 🤗 Apache-2.0! It's a bidirectional token-classification adaptation of GPT-OSS, trained to mask personally identifiable information (PII) in text. At only 1.5B params, it can even run locally in your browser!

Xenova

220,238 Aufrufe • vor 6 Monaten

Introducing LightNav-0, our first general-purpose navigation brain. Open-sourced starting today. Trained entirely in simulation, so it scales. See scalable real2sim2real transfer across robots, tasks, and scenes.
0:53

Introducing LightNav-0, our first general-purpose navigation brain. Open-sourced starting today. Trained entirely in simulation, so it scales. See scalable real2sim2real transfer across robots, tasks, and scenes.

LightOrigins

14,853 Aufrufe • vor 2 Monaten

Today we're releasing ZONOS2, our next-generation real-time TTS model with high-fidelity voice cloning. ZONOS2 is the most expressive open-source TTS model, released under Apache 2.0 and available on Zyphra Cloud on AMD. 🧵
1:30

Today we're releasing ZONOS2, our next-generation real-time TTS model with high-fidelity voice cloning. ZONOS2 is the most expressive open-source TTS model, released under Apache 2.0 and available on Zyphra Cloud on AMD. 🧵

Zyphra

335,093 Aufrufe • vor 5 Monaten

We're releasing Letta Code, a memory-first coding agent - open source (apache 2.0) - model agnostic - portable agent learning and memory
0:26

We're releasing Letta Code, a memory-first coding agent - open source (apache 2.0) - model agnostic - portable agent learning and memory

Letta

376,887 Aufrufe • vor 10 Monaten

Introducing Indic-Parler TTS - Trained on 10K hours of data, 938M params, supports 20 Indic languages, emotional synthesis, apache 2.0 licensed! 🔥 A collaboration w/ AI4Bharat & Hugging Face - w/ fully customisable speech and voice personas! Try it out directly below or use the model weights as you want! 🇮🇳/acc
1:06

Introducing Indic-Parler TTS - Trained on 10K hours of data, 938M params, supports 20 Indic languages, emotional synthesis, apache 2.0 licensed! 🔥 A collaboration w/ AI4Bharat & Hugging Face - w/ fully customisable speech and voice personas! Try it out directly below or use the model weights as you want! 🇮🇳/acc

Vaibhav (VB) Srivastav

42,212 Aufrufe • vor 1 Jahr

NEW: Kokoro 82M - APACHE 2.0 licensed, Text to Speech model, trained on < 100 hours of audio 🔥
1:54

NEW: Kokoro 82M - APACHE 2.0 licensed, Text to Speech model, trained on < 100 hours of audio 🔥

Vaibhav (VB) Srivastav

330,034 Aufrufe • vor 1 Jahr

Introducing Cosmos 3 Edge: our open frontier world model built to run on-device. Cosmos 3 Edge helps robots learn and act, autonomous vehicles understand road scenes and predict intent, and vision AI agents reason across live video for smart infrastructure. With 4B parameters and a 2B Nemotron-based reasoner, you can run it on DGX Spark, NVIDIA Jetson, and more.
0:22

Introducing Cosmos 3 Edge: our open frontier world model built to run on-device. Cosmos 3 Edge helps robots learn and act, autonomous vehicles understand road scenes and predict intent, and vision AI agents reason across live video for smart infrastructure. With 4B parameters and a 2B Nemotron-based reasoner, you can run it on DGX Spark, NVIDIA Jetson, and more.

NVIDIA AI

212,476 Aufrufe • vor 3 Monaten

Introducing the Model 73 "C-Frame" Revolver. Revealed to the public for the first time on our YouTube Channel.
0:29

Introducing the Model 73 "C-Frame" Revolver. Revealed to the public for the first time on our YouTube Channel.

Smith & Wesson Inc.

38,741 Aufrufe • vor 6 Monaten