What changed in Transformers.js from 3 to 4

4 releases numbered after 3.8.1 up to and including 4.2.0, stable releases only. 3.8.1 and 4.2.0 are the newest stable releases of 3 and 4 we track; this page follows them as new ones ship.

30 changes across 4 releases · 1 landed on more than one version

Added 24

4.0.1

  • Add support for Gemma 4also in4.1.0

4.2.0

  • Add tools parameter to TextGenerationPipeline
  • Add support for OpenAI privacy filter model

4.1.0

  • Add support for q1, q1f16, q2, and q2f16 data types

4.0.0

  • WebGPU backend completely rewritten in C++ with improved operator support for performance, accuracy, and coverage
  • WebGPU-accelerated models can now run in Node, Bun, and Deno in addition to browsers
  • Support for models exceeding 8B parameters, with tested performance of GPT-OSS 20B at approximately 60 tokens per second on M4 Pro Max
  • Support for Apertus model architecture
  • Support for FalconH1 model architecture
  • Support for Cohere's Tiny Aya models
  • Support for AFMoE model architecture
  • Support for Qwen2.5-VL, Qwen3-VL, Qwen3.5, and Qwen3.5 MoE models
  • Support for Qwen2 MoE, Qwen3 MoE, Qwen3 Next, Qwen3-VL MoE, and Olmo Hybrid models
  • Support for EuroBERT model architecture
  • Support for LightOnOCR and GLM-OCR models
  • Support for Nemotron-H model architecture
  • Support for DeepSeek-v3 model architecture
  • Support for mistral4 model architecture
  • Support for GLM-MoE-DSA model architecture
  • Support for Chatterbox model architecture
  • Support for Cohere ASR models
  • Support for SolarOpen and CHMv2 models
  • Support for Voxtral Realtime, LFM2-VL, and Granite Speech models
  • Support for Gemma3 VLM architecture
Changed 5

4.2.0

  • Use inputMetadata API for simplified internals

4.1.0

  • Improve cached generation with past_key_values via pipeline function
  • Improve tokenizer types based on input function parameters
  • Update default generation parameters

4.0.0

  • Model export strategy redesigned to use specialized ONNX Runtime Contrib Operators for improved performance
Fixed 1

4.1.0

  • Re-enable SmolVLM

Original release notes, newest first

The list above is our reading of these notes; the originals from Hugging Face are here, one fold per release.

4.0.1
What's new?

Full Changelog: 4.0.0...4.0.1

View originalPermalink

4.2.0

🚀 Transformers.js v4.2 — Tool calling, simpler internals, and privacy filtering

  • Added tools to TextGenerationPipeline in #1655
  • Use inputMetadata API for simplified internals in #1657
  • Add support for OpenAI privacy filter model in #1658

Full Changelog: 4.1.0...4.2.0

View originalPermalink

4.1.0

🚀 Transformers.js v4.1 — Gemma 4, KV cache improvements, and new quantization dtypes

  • Add support for Gemma 4 in #1627
  • Cached generation improvements (+ past_key_values via pipeline function) in #1638
  • Improve tokenizer types based on input function parameters in #1641
  • Add support for q1, q1f16, q2, and q2f16 data types in #1647
  • Re-enable SmolVLM in #1648
  • Update default generation parameters in #1649
  • Pin GitHub Actions to commit SHAs in #1626

Full Changelog: 4.0.0...4.1.0

View originalPermalink

4.0.0

🚀 Transformers.js v4

We're excited to announce that Transformers.js v4 is now available on NPM! After a year of development (we started in March 2025 🤯), we're finally ready for you to use it.

npm i @huggingface/transformers

Links: YouTube Video, Blog Post, Demo Collection

New WebGPU backend

The biggest change is undoubtedly the adoption of a new WebGPU Runtime, completely rewritten in C++. We've worked closely with the ONNX Runtime team to thoroughly test this runtime across our ~200 supported model architectures, as well as many new v4-exclusive architectures.

In addition to better operator support (for performance, accuracy, and coverage), this new WebGPU runtime allows the same transformers.js code to be used across a wide variety of JavaScript environments, including browsers, server-side runtimes, and desktop applications. That's right, you can now run WebGPU-accelerated models directly in Node, Bun, and Deno!

We've proven that it's possible to run state-of-the-art AI models 100% locally in the browser, and now we're focused on performance: making these models run as fast as possible, even in resource-constrained environments. This required completely rethinking our export strategy, especially for large language models. We achieve this by re-implementing new models operation by operation, leveraging specialized ONNX Runtime Contrib Operators like com.microsoft.GroupQueryAttention, com.microsoft.MatMulNBits, or com.microsoft.QMoE to maximize performance.

For example, adopting the com.microsoft.MultiHeadAttention operator, we were able to achieve a ~4x speedup for BERT-based embedding models.

New models

Thanks to our new export strategy and ONNX Runtime's expanding support for custom operators, we've been able to add many new models and architectures to Transformers.js v4. These include popular models like GPT-OSS, Chatterbox, GraniteMoeHybrid, LFM2-MoE, HunYuanDenseV1, Apertus, Olmo3, FalconH1, and Youtu-LLM. Many of these required us to implement support for advanced architectural patterns, including Mamba (state-space models), Multi-head Latent Attention (MLA), and Mixture of Experts (MoE). Perhaps most importantly, these models are all compatible with WebGPU, allowing users to run them directly in the browser or server-side JavaScript environments with hardware acceleration. We've released several Transformers.js v4 demos so far... and we'll continue to release more!

Additionally, we've added support for larger models exceeding 8B parameters. In our tests, we've been able to run GPT-OSS 20B (q4f16) at ~60 tokens per second on an M4 Pro Max.

New features
ModelRegistry

The new ModelRegistry API is designed for production workflows. It provides explicit visibility into pipeline assets before loading anything: list required files with get_pipeline_files, inspect per-file metadata with get_file_metadata (quite useful to calculate total download size), check cache status with is_pipeline_cached, and clear cached artifacts with clear_pipeline_cache. You can also query available precision types for a model with get_available_dtypes. Based on this new API, progress_callback now includes a progress_total event, making it easy to render end-to-end loading progress without manually aggregating per-file updates.

import { ModelRegistry, pipeline } from "@huggingface/transformers";

const modelId = "onnx-community/all-MiniLM-L6-v2-ONNX";
const modelOptions = { dtype: "fp32" };

const files = await ModelRegistry.get_pipeline_files(
  "feature-extraction",
  modelId,
  modelOptions
);
// ['config.json', 'onnx/model.onnx', ..., 'tokenizer_config.json']

const metadata = await Promise.all(
  files.map(file => ModelRegistry.get_file_metadata(modelId, file))
);

const downloadSize = metadata.reduce((total, item) => total + item.size, 0);

const cached = await ModelRegistry.is_pipeline_cached(
  "feature-extraction",
  modelId,
  modelOptions
);

const dtypes = await ModelRegistry.get_available_dtypes(modelId);
// ['fp32', 'fp16', 'q4', 'q4f16']

if (cached) {
  await ModelRegistry.clear_pipeline_cache(
    "feature-extraction",
    modelId,
    modelOptions
  );
}

const pipe = await pipeline(
  "feature-extraction",
  modelId,
  {
    progress_callback: e => {
      if (e.status === "progress_total") {
        console.log(`${Math.round(e.progress)}%`);
      }
    },
  }
);
New Environment Settings

We also added new environment controls for model loading. env.useWasmCache enables caching of WASM runtime files (when cache storage is available), allowing applications to work fully offline after the initial load.

env.fetch lets you provide a custom fetch implementation for use cases such as authenticated model access, custom headers, and abortable requests.

import { env } from "@huggingface/transformers";

env.useWasmCache = true;

env.fetch = (url, options) =>
  fetch(url, {
    ...options,
    headers: {
      ...options?.headers,
      Authorization: `Bearer ${MY_TOKEN}`,
    },
  });
Improved Logging Controls

Finally, logging is easier to manage in real-world deployments. ONNX Runtime WebGPU warnings are now hidden by default, and you can set explicit verbosity levels for both Transformers.js and ONNX Runtime. This update, also driven by community feedback, keeps console output focused on actionable signals rather than low-value noise.

import { env, LogLevel } from "@huggingface/transformers";

// LogLevel.DEBUG
// LogLevel.INFO
// LogLevel.WARNING
// LogLevel.ERROR
// LogLevel.NONE

env.logLevel = LogLevel.WARNING;
Repository Restructuring

Developing a new major version gave us the opportunity to invest in the codebase and tackle long-overdue refactoring efforts.

PNPM Workspaces

Until now, the GitHub repository served as our npm package. This worked well as long as the repository only exposed a single library. However, looking to the future, we saw the need for various sub-packages that depend heavily on the Transformers.js core while addressing different use cases, like library-specific implementations, or smaller utilities that most users don't need but are essential for some.

That's why we converted the repository to a monorepo using pnpm workspaces. This allows us to ship smaller packages that depend on @huggingface/transformers without the overhead of maintaining separate repositories.

Modular Class Structure

Another major refactoring effort targeted the ever-growing models.js file. In v3, all available models were defined in a single file spanning over 8,000 lines, becoming increasingly difficult to maintain. For v4, we split this into smaller, focused modules with a clear distinction between utility functions, core logic, and model-specific implementations. This new structure improves readability and makes it much easier to add new models. Developers can now focus on model-specific logic without navigating through thousands of lines of unrelated code.

Examples Repository

In v3, many Transformers.js example projects lived directly in the main repository. For v4, we've moved them to a dedicated repository, allowing us to maintain a cleaner codebase focused on the core library. This also makes it easier for users to find and contribute to examples without sifting through the main repository.

Prettier

We updated the Prettier configuration and reformatted all files in the repository. This ensures consistent formatting throughout the codebase, with all future PRs automatically following the same style. No more debates about formatting... Prettier handles it all, keeping the code clean and readable for everyone.

Standalone Tokenizers.js Library

A frequent request from users was to extract the tokenization logic into a separate library, and with v4, that's exactly what we've done. @huggingface/tokenizers is a complete refactor of the tokenization logic, designed to work seamlessly across browsers and server-side runtimes. At just 8.8kB (gzipped) with zero dependencies, it's incredibly lightweight while remaining fully type-safe.

import { Tokenizer } from "@huggingface/tokenizers";

// Load from Hugging Face Hub
const modelId = "HuggingFaceTB/SmolLM3-3B";
const tokenizerJson = await fetch(
  `https://huggingface.co/${modelId}/resolve/main/tokenizer.json`
).then(res => res.json());

const tokenizerConfig = await fetch(
  `https://huggingface.co/${modelId}/resolve/main/tokenizer_config.json`
).then(res => res.json());

// Create tokenizer
const tokenizer = new Tokenizer(tokenizerJson, tokenizerConfig);

// Tokenize text
const tokens = tokenizer.tokenize("Hello World");
// ['Hello', 'ĠWorld']

const encoded = tokenizer.encode("Hello World");
// { ids: [9906, 4435], tokens: ['Hello', 'ĠWorld'], ... }

This separation keeps the core of Transformers.js focused and lean while offering a versatile, standalone tool that any WebML project can use independently.

New build system

We've migrated our build system from Webpack to esbuild, and the results have been incredible. Build times dropped from 2 seconds to just 200 milliseconds, a 10x improvement that makes development iteration significantly faster. Speed isn't the only benefit, though: bundle sizes also decreased by an average of 10% across all builds. The most notable improvement is in transformers.web.js, our default export, which is now 53% smaller, meaning faster downloads and quicker startup times for users.

Improved types

We've made several quality-of-life improvements across the library. The type system has been enhanced with dynamic pipeline types that adapt based on inputs, providing better developer experience and type safety.

Bug fixes
Documentation improvements
Miscellaneous improvements
New Contributors

Full Changelog: https://github.com/huggingface/transformers.js/compare/3.8.1...4.0.0

View originalPermalink