Fetching from the wire…
Models2026-08-15 · source-backed
Danish Foundation Models trained it from scratch on 161 datasets. Across 20 benchmarks spanning English, math and code, and Danish, it beats the original HRM-Text 1B, sets a new Danish state of the art, and competes with Qwen 3.5 4B and Gemma 4 E2B. Weights are on Hugging Face. arXiv 2608.13517 The claim that matters: a licensing-clean data pipeline no longer costs an order of magnitude in capability at the small end.
Each link below shares sources, entities, or timing with this story.
Gemma built by Google / Shared entities / Shared topic / Earlier coverage
Linked by a graph relationship (Gemma built by Google); both cover E2B, Gemma, Qwen; overlapping topics (beat, model, qwen).
Linked by a graph relationship (Gemma built by Google); both cover E2B, Gemma, Qwen; overlapping topics (benchmark, model).
Alibaba released Qwen / Shared entities / Shared topic / Earlier coverage / Tension
Linked by a graph relationship (Alibaba released Qwen); both cover Gemma, Qwen; overlapping topics (benchmark, capability, model).
E2B partners with OpenAI / Shared entities / Shared topic / Earlier coverage
Linked by a graph relationship (E2B partners with OpenAI); both cover Hugging Face, Qwen; overlapping topics (face, model, qwen).
Linked by a graph relationship (E2B partners with OpenAI); both cover Qwen, Weights; overlapping topics (beat, code, model).
Linked by a graph relationship (E2B partners with OpenAI); both cover Gemma, Qwen; overlapping topics (benchmark, cost, model).
E2B partners with OpenAI / Shared entity: Hugging Face / Same source domain / Shared topic / Earlier coverage / Tension
Linked by a graph relationship (E2B partners with OpenAI); both cover Hugging Face; reported by the same outlet (arxiv.org).
E2B partners with OpenAI / Shared entity: Hugging Face / Same source domain / Shared topic / Earlier coverage
Linked by a graph relationship (E2B partners with OpenAI); both cover Hugging Face; reported by the same outlet (arxiv.org).