all-MiniLM-L6-v2 still trending on Hugging Face, its creator says stop using it
tomaarsen · x · 2026-09-16
Tom Aarsen, maintainer of Sentence Transformers, noticed that the 2021-era embedding model all-MiniLM-L6-v2 is still trending on Hugging Face. He says it's time to move on: "it's not 2021 anymore, you're leaving performance on the table." He points to newer alternatives such as IBM's granite-embedding-30m-english (30M parameters, 2M+ cumulative downloads, Apache 2.0).
More from Models
- Altman says internal post-Astra OpenAI model can solve problems the world's best mathematicians cannot — rohanpaul_ai · 2026-09-16
- Agent randomly references a money quote the user never said while editing unrelated text — Kyrannio · 2026-09-16
- OpenAI's new quirk: chat mode now has a usage cap while work mode doesn't — koltregaskes · 2026-09-16
- MindTopo benchmark: best MLLM scores 54.1% vs 97.4% human on topological reasoning; GPT-6 Astra needs 8+ hours per task — yining_hong · 2026-09-16
- HF researcher publicly questions Claude limits: monthly exhausted but weekly 84% left — NielsRogge · 2026-09-16
- Meta's promised Muse Spark open weights are over a month late and counting — RishiFurfox · 2026-09-16