Linkup open-sources SPARSEUP, strongest public sparse retriever under 150M, beating SparseEncoder models by a wide margin
antoine_chaffin · x · 2026-09-18
Linkup's research team has released SPARSEUP, an open-source sparse retrieval model the team calls a missing piece in the open-source ecosystem.
- Positioned as the strongest public sparse retriever at under 150M parameters
- Reported to beat existing SparseEncoder models by a large gap on general-purpose retrieval/search benchmarks
- tomaarsen (maintainer of sentence-transformers) amplified the release, calling the margin impressive
A notable new efficient baseline for anyone building local retrieval or RAG pipelines.
Related event: Linkup Open-Sources SparseUp: 149M-Parameter Sparse Retriever Tops BEIR-13(12 posts)→
More from Models
- LightOnOCR-3 Reads 16th-Century Manuscripts and Ancient Greek Without Training — IgorCarron · 2026-11-02
- 'You Can Feel the Gradient Slopes': Dev Contrasts Benchmaxxed RL Models vs General Ones — theteknosaur · 2026-11-02
- LightOnOCR-3 Launches: Tops FRBench, Adds Layout Structure and Chart Extraction — IgorCarron · 2026-11-02
- NVIDIA's Kumo Is a Family of Four Tabular Foundation Models, Not Just One — pandeyparul · 2026-11-02
- SemiAnalysis: safety classifiers are underrated — Meta's Muse tops cyber benchmark at 35.2% — ThomasScialom · 2026-11-02
- DeepSeek V4.1 Flash 1017 wins over a longtime closed-source-only user: fast, cheap, reliable — _bachrc · 2026-11-02