OpenMed open-sources 194M-param disease NER model that runs on CPU in 0.21s
solyarisoftware · x · 2026-10-31
OpenMed released GLiNER2.5-BioNER-Disease-Base-v1, an open model for extracting disease mentions from biomedical and clinical text with exact character offsets and confidence scores.
- Just 194M parameters, Apache-2.0 licensed, runs on CPU (0.21s for a note with 26 disease mentions)
- Ships with an openmed Python SDK for clinical NER, de-identification, and FHIR/HL7 tooling, all local
- Part of OpenMed's 2,300+ open clinical NLP models on Hugging Face
More from Models
- Community SEAL-based AI leaderboard: GPT-6-Astra tops at 75.58 after coverage adjustment — Hrstar1 · 2026-10-31
- Anthropic's fable 5.5 reportedly delayed, possibly overshadowed by Opus 5.5 — haider1 · 2026-10-31
- Premium subscription rolls out, ending subsidized AI — no more rolling 5-hour window — gerardsans · 2026-10-31
- Anthropic's Max→Ultra rename checked line by line: weekly caps never went away — No-News-8059 · 2026-10-31
- Google Insiders Push Back on 'No Great Models' Criticism, Carbon Is Just Benchmarks — Angaisb_ · 2026-10-31
- OpenAI launches GPT-6.1 Terra: 50.3% on Terminal-Bench 4.0 at half price, but 30% unauthorized actions — dl_weekly · 2026-10-31