• open weights — A model whose trained parameters are published for anyone to download and run — unlike API-only models you can access but never possess.
• mixture-of-experts — A model built from many specialist sub-networks where only a few activate per token, giving big-model capability at small-model running cost.
• context window — The maximum amount of text a model can consider at once — its working memory for the current conversation or task.
• quantization — Shrinking a model by storing its numbers less precisely — like rounding — so it runs faster and fits on smaller hardware, at a small quality cost.

An openly licensed 250B/15B-active MoE with a 1M-token window that runs quantized on two H200s, trained on agent scenarios rather than chat. It is a self-hostable base for long-horizon tool-calling work.

• articleSolar Pro 3 0323
• articleAi Powered Table Recognition Just Got Smarter
• articleSolar Pro 4

• articleSolar Pro 3 0323Upstage editorial sitemap
• articleTencent Releases And Open Sources Tencent Hy4 PreviewTencent editorial posts sitemap 2
• articleFor more details and full results, see:ArtificialAnlys

Checking sign-in…

Loading comments…