Microsoft's MAI finishes in-house 3T-parameter pretrained base models, post-training results coming
soumitrashukla9 · x · 2026-10-16
Mustafa Suleyman announced that MAI has built state-of-the-art pretrained base models in the 3T-parameter weight class entirely in-house, with post-training results coming soon and details in a technical blog post.
Reposters highlight it as a strong read on how bigger models are trained. The move marks a major step in Microsoft's independent frontier-model efforts outside its OpenAI partnership.
Related event: Microsoft AI Completes 3T-Parameter Pre-trained Base Model(4 posts)→
More from Models
- Gemini 4 Argon hits AssemblyAI's LLM Gateway, tops voice bench at 99.5 across 50+ models — AssemblyAI · 2026-10-16
- Meta's open-weight Muse Spark Open hits Ollama with 1M-token context and Claude Code support — ollama · 2026-10-16
- 'Opus 5.5' collage demos spark claim: models have taste, no moat — yuwen_lu_ · 2026-10-16
- PrismML ships Bonsai 2 ternary models: 9B fits in 2GB for local AI — gajesh · 2026-10-16
- Apple MLX Runs 816B Muse Spark Open at 36+ Tokens/s on Four Mac Studios — andrejusb · 2026-10-16
- vLLM Ships Day-0 Support for Meta's 816B Open-Weight Muse Spark Open — woosuk_k · 2026-10-16