Motif Technologies

We build foundational AI models across multiple domains.
Check out Motif 3:

[Motif Technologies @motif_tech]

📢 About Motif 3📢
▪️ Decoder-only MoE language model with 314B parameters, 13.2B active.
▪️ Scored 47 on @ArtificialAnlys Intelligence Index, 5th among all open-weight models, ahead of @MiniMax_AI M3, @thinkymachines Inkling, @nvidia Nemotron, and all other models developed outside of China.
▪️ Built from scratch around a novel attention architecture (GDLA) and trained on only 768 B200s in ~5 months.
▪️ MIT license.

(1/3)

[Motif Technologies @motif_tech]

📣 Motif-3 is free on Infron through Sep 29 📣
Give it a spin and let us know what you think!

[Infron @InfronAI]

Motif 3 scores 35.3 on tau-3 Banking, ahead of DeepSeek V4 Pro in @motif_tech's published comparison: https://t.co/TjbARgL5RB

It activates just 13.2B parameters per token.

Free access on Infron. Report and API details in the first reply.

[Infron @InfronAI]

Motif 3 is free on Infron for one month.

314B total parameters, 13.2B active per token, a 256K context window, and MIT-licensed weights.

Try it with model ID motif/motif-3: https://t.co/TjbARgKy23

Built by @motif_tech. Details in the first reply.

[Motif Technologies @motif_tech]

Thank you @interconnectsai for the spotlight on Motif-3.

"Motif is one of the few hidden gems out there, showcasing innovation in their model training with very limited resources compared to others. Motif-3 comes with an MIT license and impressive scores for its size. Given the trajectory of model releases from Motif 2.6B, which we covered in 2025 and Motif-2-12.7B, the improvements are impressive."

[Interconnects AI @interconnectsai]

Artifacts 24: Motif-3, GLM-5.3, Hy4-preview and open model licenses. In this issue, the 25 models from july/aug/sept you should be aware of, from:

InclusionAI @TheInclusionAI (4)
Qwen @alibaba_qwen (3)
Z ai @Zai_org (2)
DeepSeek @deepseek_ai (2)
Motif Technologies @motif_tech
Dots Studio @dotsstudioai
Tencent @TencentGlobal
NVIDIA @NVIDIAAI
IBM @IBM
Institute of Foundation Models @IFM_AI
Trillion Labs @TrillionLabs
SenseTime @SenseTime_AI
Meta @AIatMeta
Liquid AI @liquidai
Cohere @Cohere_Labs
Superwhisper @superwhisper
Google @GoogleAI
MiniMax @MiniMax_AI

Read the issue below.

[SemiAnalysis @SemiAnalysis_]

Korea’s Trillion-Dollar Sovereign AI Investment: Nvidia Wins, Hynix Loses
Korea hosts a Squid Games, National AI Tournament,
the best non-Chinese open source model gets eliminated,
why Nvidia needs open source, implications for Hynix and Samsung

https://t.co/E3eiJx4VzN

[Motif Technologies @motif_tech]

@SemiAnalysis_ Thanks for the spotlight - we’re proud of what we’ve built from scratch.
Our weights are MIT, check out more in the links below.
Model card: https://t.co/k5smtDGt2K
Technical report: https://t.co/2jbC4tRRNm

[Motif Technologies @motif_tech]

Model card: https://t.co/k5smtDGt2K
Technical report: https://t.co/2jbC4tRRNm

API is also coming soon - stay tuned!

(3/3)

[Motif Technologies @motif_tech]

📢 About Motif 3📢
▪️ Decoder-only MoE language model with 314B parameters, 13.2B active.
▪️ Scored 47 on @ArtificialAnlys Intelligence Index, 5th among all open-weight models, ahead of @MiniMax_AI M3, @thinkymachines Inkling, @nvidia Nemotron, and all other models developed outside of China.
▪️ Built from scratch around a novel attention architecture (GDLA) and trained on only 768 B200s in ~5 months.
▪️ MIT license.

(1/3)

[Motif Technologies @motif_tech]

Motif 3 spikes on long-horizon agentic tasks, mathematical reasoning, scientific knowledge, and hallucination-sensitive evaluation.

(2/3)

[Motif Technologies @motif_tech]

Jisoo Lee, one of the driving forces behind Motif 3, will share the story of its development journey and how NVIDIA technologies were leveraged along the way.

If you’re interested, register for the session below!

⏰ Time: Wednesday, August 26, 2:00–3:00 PM
📌 Register here: https://t.co/MgXUsmX2xH

Motif 3 개발의 주역이신 이지수님께서 Motif 3 개발 여정과 Nvidia 기술들을 어떻게 활용했는지에 대해서 설명해주실 예정입니다.

관심있으신 분들은 아래 링크에서 일정 등록하세요!

⏰ 일시 : 8월 26일(수) 오후 2시 - 3시
📌 일정 등록하기: https://t.co/MgXUsmX2xH

[NVIDIA Korea @NVIDIAKorea]

🔔 [D-1 LIVE] 내일 오후 2시! 내 도메인에 딱 맞는 AI 모델 구축 라이브 스트리밍

Nemotron 3.5 Lightning 기반 SFT·LoRA 파인튜닝부터 모델 평가, NeMo RL 미리보기까지 — NVIDIA 전문가가 실무 핵심을 단계별로 ���어드립니다. 스페셜 게스트 Motif Technologies의 Blackwell 기반 K-AI 오픈 모델 구축 비하인드도 놓치지 마세요.
⏰ 일시: 8월 26일(수) 오후 2시 - 3시
📌 일정 등록하기: https://t.co/PBTQahB5W6"

[Motif Technologies @motif_tech]

Motif 3 is the highest-scoring open-weight model developed outside China—47 on the Artificial Analysis Intelligence Index.

Motif 3 API is coming soon. Stay tuned.

Thank you, @ArtificialAnlys, for the coverage.

[Artificial Analysis @ArtificialAnlys]

South Korea has once again established a clear #3 position in the global AI race, trailing only the United States and China. The depth and vibrancy of Korea’s AI ecosystem is supported by strong domestic talent, public investment, and the incentives created by Korea’s Sovereign AI Foundation Model project

A number of South Korean labs, including Motif Technologies, Upstage, SK Telecom, and LG AI Research, have now scored above 30 on the Artificial Analysis Intelligence Index. This concentration of competitive model developers highlights the growing density of Korea’s domestic AI ecosystem. Among them, Motif Technologies and Upstage have models scoring above 40, making them the highest-scoring models on the Intelligence Index developed outside the United States and China.

Leading models from each lab include:

➤ Motif Technologies’ Motif 3 scored 47 on the Intelligence Index (314B total parameters, 13B active; open weights).

➤ Upstage’s Solar Pro 4 scored 42 on the Intelligence Index. It is a proprietary reasoning model.

➤ SK Telecom’s A.X K2 scored 35 on the Intelligence Index (692B total parameters, 33B active; open weights).

➤ LG AI Research’s K-EXAONE 2.0 scored 31 on the Intelligence Index (750B total parameters, 37B active; open weights).

Outside the competition, Korea’s model-development ecosystem has continued to broaden. Trillion Labs, Korea Telecom (KT), and other AI labs are building out their own model families, adding to a domestic field that is considerably deeper and more competitive than it was a year ago.

[Motif Technologies @motif_tech]

@ArtificialAnlys 🚀LFG!!!!!

[Motif Technologies @motif_tech]

@Alisvolatprop12 🔥🔥🔥

[Motif Technologies @motif_tech]

@eliebakouch
Always appreciate the review!

[elie @eliebakouch]

new huge oss release: motif 3 final checkpoint with a tech report and base model

tech report include ablations on GLDA (their new attention variant), expert stabilization, dataset (they use nemotron 3 mixture for 70% of the pt corpus) and much more

https://t.co/8Tb5SaAePH

[Motif Technologies @motif_tech]

@NVIDIAAI Always appreciate the support!

[Motif Technologies @motif_tech]

Motif 3 is officially here.
Today, we’re releasing Motif 3 Base and Motif 3.

Motif 3 Base is our pretrained foundation model, while Motif 3 is built on top of it with post-training using NVIDIA NeMo-RL.

Both models were developed with the support of Korea's Ministry of Science and trained on NVIDIA B200 GPUs.

With Motif 3, we’re taking our first step into the frontier LLM race.

There’s still a long way to go, but we believe we’ve built a model that deserves to be in the race.
We’ve shared the details in our technical report and blog post.

In collaboration with NVIDIA, we’re also releasing an NVFP4 version of Motif 3.

All models will be available on Hugging Face.
Links are in the comments.

[Motif Technologies @motif_tech]

https://t.co/44kGDbD7x9

[Motif Technologies @motif_tech]

https://t.co/k5smtDGt2K

[Motif Technologies @motif_tech]

https://t.co/0LsdXOntXO

[Junghwan Lim @junghwan_l]

We’re in the middle of developing a video generation model.

Sharing a few mid-training results below. You can find further information at here: https://t.co/BzeX4mAIIq

Model weight and detailed information would be released once the development is complete.

#VideoGeneration

[Motif Technologies @motif_tech]

Appreciate the update, @natolambert — thanks for adding Motif to the list. Also, shoutout to @eliebakouch in the replies for surfacing us.

Motif is now listed in the same tier as @ByteDanceOSS and @Baidu_Inc , and one tier above @AIatMeta , @cohere , and @Huawei .

[Nathan Lambert @natolambert]

@deepseek_ai @AlibabaGroup @crystalsssup Okay okay, due to reasonable feedback we added:
@cohere for their non commercial models
@ServiceNow with Apriel, I like folks there (and pipeline rl)
Motif
@tngtech as a shout out for awesome hacks and merges of big MoEs

This is DEFINITELY right, no take backs