Home Movements Mixture of experts Models split into many expert blocks with only a few active per token, so they grow in size without growing in cost. Named by Shazeer et al., Google Brain: Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer (Jan 23, 2017). Also called MoE, Sparse models, Sparse mixture of experts.
Since 2017 Last 28 days
Index 0 to 100, monthly 0 38 76 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 Origin
Signals Signal Value Reads as Hacker News stories, last 12 months 93 stories, +182% on the 12 months before 93 stories, +182% on the 12 months before Adoption arXiv papers, last 12 months 1,835 papers, +93% on the 12 months before 1,835 papers, +93% on the 12 months before Adoption Wikipedia views, August 2026 8,562, -21% on a year before 8,562, -21% on a year before Decline Product releases naming it 13 since Sep 1, 2025 13 since Sep 1, 2025 Adoption GitHub repositories 2,012 2,012 Adoption
Releases 13 releases since Sep 1, 2025 Name Date Transformers Release 5.17.0 Hugging Face · Sep 10, 2026 2w 2 weeks ago Sep 10, 20262w 2 weeks ago Announcing Cohere's North Small Translate Cohere · Sep 9, 2026 2w 2 weeks ago Sep 9, 20262w 2 weeks ago Zhipu AI GLM 5.3 now available as a Databricks-hosted model Databricks · Aug 29, 2026 3w 3 weeks ago Aug 29, 20263w 3 weeks ago Hy4 Preview now available on AI Gateway Vercel · Aug 28, 2026 4w 4 weeks ago Aug 28, 20264w 4 weeks ago Workers AI - Z.ai GLM-5.3 Flash now available on Workers AI Cloudflare · Aug 26, 2026 4w 4 weeks ago Aug 26, 20264w 4 weeks ago Ling 3.0 Flash is now available on AI Gateway Vercel · Jul 23, 2026 2mo 2 months ago Jul 23, 20262mo 2 months ago Laguna S 2.1 is now available on AI Gateway Vercel · Jul 21, 2026 2mo 2 months ago Jul 21, 20262mo 2 months ago Thinking Machine Labs Inkling now available as a Databricks-hosted model in Public Preview Databricks · Jul 15, 2026 2mo 2 months ago Jul 15, 20262mo 2 months ago
GitHub projects 2,012 repositories Name Created Stars deepseek-ai/DeepSeek-VL2 DeepSeek-VL2: Mixture-of-Experts Vision-Language Models for Advanced Multimodal Understanding · Dec 13, 2024 1y 1 year ago Dec 13, 20241y 1 year ago 5,375 deepseek-ai/DeepSeek-V2 DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Model · Apr 22, 2024 2y 2 years ago Apr 22, 20242y 2 years ago 5,041 PKU-YuanGroup/MoE-LLaVA 【TMM 2025🔥】 Mixture-of-Experts for Large Vision-Language Models · Dec 14, 2023 2y 2 years ago Dec 14, 20232y 2 years ago 2,324 deepseek-ai/DeepSeek-MoE DeepSeekMoE: Towards Ultimate Expert Specialization in Mixture-of-Experts Language Models · Jan 2, 2024 2y 2 years ago Jan 2, 20242y 2 years ago 1,976 XueFuzhao/OpenMoE A family of open-sourced Mixture-of-Experts (MoE) Large Language Models · Aug 8, 2023 3y 3 years ago Aug 8, 20233y 3 years ago 1,699 XueFuzhao/awesome-mixture-of-experts A collection of AWESOME things about mixture-of-experts · Mar 30, 2022 4y 4 years ago Mar 30, 20224y 4 years ago 1,287
Related movements Movement Stage Open-weight models Models whose trained weights anyone can download, run and fine-tune: Llama, Qwen, DeepSeek, Mistral and more. Inference chips Accelerators built to serve models cheaply and fast rather than to train them: TPUs, LPUs, wafer-scale and custom silicon. Reasoning models Models trained with reinforcement learning to think step by step, spending more compute at answer time.
History Date What changed Sep 24, 2026 Tracking started: emerged January 2017, peak, 3 other names recorded
Sources: Curve: Hacker News story titles, Wikipedia pageviews and arXiv papers by month, refreshed Sep 24, 2026. Related entities from the fru.dev sites' public APIs, matched by name. How stages work .
Suggest a correction 