Industry
Transformers.js monthly downloads 🤯📈 2023/03 ▏3.2K 2024/03 █ 266K 2025/03 ██ 764K 2026/03 ████████████ 4.4M Thanks so much to this amazing…
Transformers.js, a library that enables running state-of-the-art Hugging Face machine learning models directly in the browser with no server required, has experienced explosive NPM download growth ...
Transformers.js, a library that enables running state-of-the-art Hugging Face machine learning models directly in the browser with no server required, has experienced explosive NPM download growth — from approximately 3,200 monthly downloads in March 2023 to 4.4 million in March 2026, representing a ~1,375× increase in three years. The library, maintained by Xenova (Joshua), uses ONNX Runtime under the hood and supports a wide range of tasks including NLP, computer vision, audio, and multimodal inference. This growth coincides with major releases including v3 (with WebGPU support) and v4 (featuring a rewritten C++ WebGPU runtime enabling hardware-accelerated inference across browsers, Node.js, Bun, and Deno).
Related
- Did the famous @huggingface HQ tour in Paris! Huge thanks to @xenovacom 😊 Such an amazing space!
- favorite AGI/sci-fi vibe these days is coding a robot code together with the robot here vibe-pluging @ElevenLabs in @reachymini for a talk l…
- hermes agent traces on Hf would be pretty neat attn: @Teknium @NousResearch @ClementDelangue https://huggingface.co/changelog/agent-trace-vi…
- Refiant raises $5M to refine AI models with ‘nature-inspired’ energy efficiency
Source: industry