Alternatives and similar repositories for transformers.js-benchmarking

Users that are interested in transformers.js-benchmarking are comparing it to the libraries listed below

• webmachinelearning / awesome-webnn
  ⚡Delightful WebNN resources, curated list of awesome things around WebNN ecosystem.😎
  ☆65Updated 3 weeks ago
• xenova / model-explorer
  Browse, search, and visualize ONNX models.
  ☆32Updated 2 months ago
• frost-beta / train-model-with-js
  Train text generation model with JavaScript.
  ☆15Updated last year
• FL33TW00D / laserbeak
  Add local LLMs to your Web or Electron apps! Powered by Rust + WebGPU
  ☆102Updated 2 years ago
• epicure / llama2.js
  Inference Llama 2 in one file of pure JavaScript(HTML)
  ☆33Updated last month
• xenova / phonemizer.js
  Simple text to phones converter using eSpeak NG.
  ☆30Updated 6 months ago
• cztomsik / ggml-js
  JavaScript bindings for the ggml-js library
  ☆43Updated 3 months ago
• ngxson / ggml-easy
  Thin wrapper around GGML to make life easier
  ☆36Updated 3 weeks ago
• frost-beta / llama3.js
  A JavaScript implementation of Llama 3 using node-mlx.
  ☆73Updated last year
• FL33TW00D / deCoreML
  Find out why your CoreML model isn't running on the Neural Engine!
  ☆25Updated last year
• FL33TW00D / embd
  GPU accelerated client-side embeddings for vector search, RAG etc.
  ☆66Updated last year
• FL33TW00D / coremlprofiler
  Profile your CoreML models directly from Python 🐍
  ☆28Updated 9 months ago
• FL33TW00D / wattkit
  ☆14Updated 7 months ago
• Narsil / hf-chat
  ☆26Updated 7 months ago
• cloudflare / workers-wonnx
  ☆46Updated 3 months ago
• bwasti / brr.js
  trying to make WebGPU a bit easier to use
  ☆16Updated last year
• fixie-ai / thefastest.ai
  Website with current metrics on the fastest AI models.
  ☆41Updated 8 months ago
• keithamus / observable-polyfill
  A polyfill for the WICG Observable
  ☆12Updated last week
• mybigday / llama.node
  Node.js binding of llama.cpp
  ☆12Updated last week
• pipecat-ai / pipecat-client-web-transports
  A mono-repo to house the various supported Transport options to be used with Pipecat's client-js package
  ☆26Updated last week
• keithwhor / wavtools
  Record and stream WAV audio data in the browser across all platforms
  ☆85Updated 8 months ago
• wizenheimer / tinylm
  Browser based ML Inference | OpenAI compliant | Run models like DeepSeek, Llama 3.2, NomicEmbed, KokoroTTS, and more
  ☆37Updated 4 months ago
• microsoft / webnn-developer-preview
  ☆60Updated last week
• jasonmayes / headless-chrome-nvidia-t4-gpu-support
  Using headless Chrome on server side environments for true client side browser emulation with NVIDIA T4 GPUs for Web AI model testing or …
  ☆79Updated last year
• hyparam / hyllama
  llama.cpp gguf file parser for javascript
  ☆43Updated 7 months ago
• jasonmayes / web-ai-model-proxy-cache
  Retrieve large (GBs) AI binary model files from cloud, cache locally as sharded blobs to load faster on 2nd page load, returns stored fil…
  ☆28Updated 2 months ago
• ggerganov / bert.cpp
  GGML implementation of BERT model with Python bindings and quantization.
  ☆26Updated last year
• replicate / cog-triton
  A cog implementation of Nvidia's Triton server
  ☆17Updated 8 months ago
• whitphx / transformers.js.py
  ☆84Updated this week
• replicate / cog-flan-models
  Code for training & inference with FLAN family of models
  ☆17Updated 2 years ago