A Sovereign, Open-Source Foundation Model for German and English · HackerPapers discussionshttps://hackerpaper.kaipfister.de/p/2607.09424/Collected HN comments and submissions linking this paper.enMon, 02 Nov 2026 11:16:22 GMTA Sovereign, Open-Source Foundation Model for German and English — mentioned by zurferhttps://news.ycombinator.com/item?id=48979854urn:hackerpapers:mention:2607.09424:48979854Mon, 20 Jul 2026 15:02:29 GMT<p>more interesting link: https://arxiv.org/html/2607.09424v2 and &gt; Long-context serving efficiency. Soofi S combines frontier-level capability with the highest measured aggregate long-context decode TPS, and unlike full-attention dense baselines maintains high throughput as context grows. Panel (1(a)) plots Capability Index versus measured aggregate decode TPS/GPU at 40K context and batch 32. The Capability Index averages five benchmark groups, i.e., Code, GSM8K, GPQA-Diamond, English aggregate, and German aggregate, after normalizing each group to the best plotted model. Aggregate decode…</p><p><a href="https://hackerpaper.kaipfister.de/p/2607.09424/">Paper and discussion history</a>. A mention is not an endorsement.</p>cs.CLA Sovereign, Open-Source Foundation Model for German and English — mentioned by bekleinhttps://news.ycombinator.com/item?id=48939202urn:hackerpapers:mention:2607.09424:48939202Thu, 16 Jul 2026 19:35:33 GMT<p>Some other (as in better) sources I found: - https://huggingface.co/spaces/Soofi-Project/Pretraining-Tech... - https://arxiv.org/pdf/2607.09424</p><p><a href="https://hackerpaper.kaipfister.de/p/2607.09424/">Paper and discussion history</a>. A mention is not an endorsement.</p>cs.CL