The Transformer was born in 2017 for translation — Google proposed it to replace its machine-translation stack. Nine years later, Cohere, a company founded by authors of that paper, has circled back to the starting point: North Small Translate, a dedicated translation LLM with open weights on Hugging Face.

What shipped

North-Small-Translate-1.0 is a sparse Mixture-of-Experts decoder: 218B total parameters, only 25B active per token. The architecture has 128 experts, with 8 selected per token plus shared experts. Attention layers interleave sliding-window attention (window 4096, with RoPE) and global attention (no positional embeddings) at a 3:1 ratio, as first introduced in Command A; the router applies sigmoid activation over the expert logits and normalizes over the selected top-k.

It covers 50 languages (32 high-resource plus 18 additional), with 16K input / 16K output context, text in and text out. Three quantizations ship: BF16 needs 4x B200 or 8x H100, FP8 needs 2x B200 or 4x H100, and the 4-bit NVFP4 build fits on 1x B200 or 2x H100. The license is CC BY-NC 4.0 — open for research, with commercial use routed through RWS's Language Weaver platform.

Benchmarks: specialist vs generalist

On the WMT26 all-languages evaluation Cohere ran itself (with GPT-5.6-Sol as judge), North Small Translate scores 83.60 — ahead of Qwen 3.5 397B A17B (81.56), DeepL NextGen (81.37), Gemma 4 31B (79.46), GLM 5.2 FP8 (76.50) and Google Translate (68.20). The "Agentic" variant, which finds and fixes its own translation errors, reaches 84.36.

Long documents are where the gap widens most: translating two book chapters in a single call, it scores 48.9 versus Google Translate's 21.3 and Gemma 4 31B's 19.4 — more than double the generalists.

The efficiency math

Under identical hardware and concurrency, output throughput hits 112 tokens per second against Gemma 4 31B's 81 (39 vs 30 at high concurrency) — roughly 30-38% more. The commercial configuration averages just 661 tokens per task at $0.000676; the comparison point Cohere gives, Gemini 3.1 Pro Preview (high), costs $0.038928 per task — 5,762% more.

A bucket of cold water

Every number above is Cohere-run. MarkTechPost advises treating the scores as vendor-reported until independent WMT26 results appear, and benchmark aggregator BenchLM likewise keeps the model out of weighted rankings, display-only. Market response has been lukewarm: the HF model card shows roughly 40 downloads in the past month.

But the signal is real: after Command A+ and North Mini Code, this is Cohere's third open-weight release in four months on the same 218B/25B footprint — and this time it is aimed squarely at DeepL's home turf. For sovereign-AI deployments (localization, government, regulated industries) where data cannot leave the premises, the choice used to be between a closed API and a generalist model moonlighting as a translator. Now there is a third option that beats DeepL on the vendor's own benchmark and fits on two H100s.

Nine years ago the Transformer was built to make machines translate; then generalization swallowed every specialist. The counterattack starts with a model card that fits on two H100s.

References: Cohere blog · HF model card (CohereLabs/North-Small-Translate-1.0) · MarkTechPost coverage