Introducing SubQ - a major breakthrough in LLM intelligence.
It is the first model built on a fully sub-quadratic sparse-attention architecture (SSA),
And the first frontier model with a 12 million token context window which is:
- 52x faster than FlashAttention at 1MM tokens
- Less than 5% the cost of Opus
Transformer-based LLMs waste compute by processing every possible relationship between words (standard attention).
Only a small fraction actually matter.
@subquadratic finds and focuses only on the ones that do.
That's nearly 1,000x less compute and a new way for LLMs to scale.
Xiaomi MiMo-V2.5 is now officially open-sourced!
MIT License, supporting commercial deployment, continued training, and fine-tuning - no additional authorization required.
Two models, both supporting a 1M-token context window :
• MiMo-V2.5-Pro: built for complex agent and coding tasks, ranking No.1 among open-source models on GDPVal-AA and ClawEval
• MiMo-V2.5: a native omni-modal model with strong agent capabilities
A model's value isn't measured by rankings alone — it's measured by the problems it solves.
Let's build with MiMo now!
🤗 Weights: https://t.co/w7wNtXj9Rm
📄 Blog: https://t.co/bPaaWMRI0g
@sharno3@mansy2 + ال٨ دول هيكون الاداء مقبول مش افضل حاجة! طبعا ده بعد مراجعة specs احنا غلابة ومش بنشغل الحاجات دي
أنا كمان فكرت في حاجة تانية اشوف تكلفة التشغيل شهريا ع حاجة كلاود لقيت تقريبا انها داخلة ف ٣٥ الف دولار قلت يابلاش ودخلت نمت 😂
طيب عشان السؤال دة اتكرر كتير مؤخرا بحكم إن كذا حد اعرفه بينقل أوروبا أو بيغير شغله ، ازاى تتفاوض على مرتبك فى أوروبا لو انت شغال فى مجال السوفتوير. أنا شخصيا أول ما جيت هنا كنت underpaid بشدة واتعلمت التفاوض عالمرتب the hard way والحمد لله ساعدت كذا حد ياخد مرتب أعلى. ثريد.