Hacker News: xenova

Bonsai 27B: A 27B-Class model that runs on a phone

xenova — Tue, 14 Jul 2026 17:50:48 +0000

Article URL: https://prismml.com/news/bonsai-27b

Comments URL: https://news.ycombinator.com/item?id=48910545

Points: 706

# Comments: 252

1-Bit and Ternary Bonsai Image 4B: Image Generation for Local Devices

xenova — Tue, 26 May 2026 18:55:39 +0000

Article URL: https://prismml.com/news/bonsai-image-4b

Comments URL: https://news.ycombinator.com/item?id=48284221

Points: 3

# Comments: 0

New comment by xenova in "Ternary Bonsai: Top Intelligence at 1.58 Bits"

xenova — Tue, 21 Apr 2026 14:32:43 +0000

yep! :) https://huggingface.co/spaces/webml-community/bonsai-ternary...

ML-intern: open-source ML engineer that reads papers, trains and ships models

xenova — Tue, 21 Apr 2026 13:26:02 +0000

Article URL: https://github.com/huggingface/ml-intern

Comments URL: https://news.ycombinator.com/item?id=47848508

Points: 3

# Comments: 0

New comment by xenova in "[dead]"

xenova — Thu, 24 Jul 2025 15:46:10 +0000

This demo runs Voxtral-Mini-3B, a new audio language model from Mistral, enabling state-of-the-art audio transcription directly in your browser. Everything runs locally, meaning none of your data is sent to a server (and your transcripts are stored on-device).

New comment by xenova in "Kokoro WebGPU: Real-time text-to-speech 100% locally in the browser"

xenova — Fri, 07 Feb 2025 17:31:05 +0000

We have released a bunch of speech recognition demos (using whisper, moonshine, and others). For example:

- https://huggingface.co/spaces/Xenova/whisper-web

- https://huggingface.co/spaces/Xenova/whisper-webgpu

- https://huggingface.co/spaces/Xenova/realtime-whisper-webgpu

- https://huggingface.co/spaces/webml-community/moonshine-web

New comment by xenova in "Kokoro WebGPU: Real-time text-to-speech 100% locally in the browser"

xenova — Fri, 07 Feb 2025 15:30:08 +0000

It took some time, but we finally got Kokoro TTS (v1.0) running in-browser w/ WebGPU acceleration! This enables real-time text-to-speech without the need for a server. Looking forward to your feedback!

Kokoro WebGPU: Real-time text-to-speech 100% locally in the browser

xenova — Fri, 07 Feb 2025 15:30:08 +0000

Article URL: https://huggingface.co/spaces/webml-community/kokoro-webgpu

Comments URL: https://news.ycombinator.com/item?id=42973769

Points: 227

# Comments: 53

New comment by xenova in "[dead]"

xenova — Thu, 16 Jan 2025 23:20:01 +0000

NPM package: https://www.npmjs.com/package/kokoro-js GitHub: https://github.com/hexgrad/kokoro

New comment by xenova in "[dead]"

xenova — Wed, 01 Jan 2025 15:24:04 +0000

For those interested in learning more, the source code is available on GitHub: https://github.com/huggingface/transformers.js-examples/tree...

Transformers.js v3: WebGPU Support, New Models and Tasks, and More

xenova — Tue, 22 Oct 2024 15:22:01 +0000

Article URL: https://huggingface.co/blog/transformersjs-v3

Comments URL: https://news.ycombinator.com/item?id=41915188

Points: 1

# Comments: 0

SAM 2: Segment Anything in Images and Videos

xenova — Mon, 29 Jul 2024 22:52:56 +0000

Article URL: https://github.com/facebookresearch/segment-anything-2

Comments URL: https://news.ycombinator.com/item?id=41104523

Points: 824

# Comments: 147

New comment by xenova in "[dead]"

xenova — Mon, 10 Jun 2024 13:41:19 +0000

It uses OpenAI's set of whisper models, which support multilingual transcription and translation across 100 languages. Since the models run entirely locally in your browser (thanks to Transformers.js), no data leaves your device! Huge for privacy!

Source code: https://github.com/xenova/whisper-web/tree/experimental-webg...

New comment by xenova in "Transformers.js – Run Transformers directly in the browser"

xenova — Thu, 11 Apr 2024 21:54:00 +0000

We have some other WebGPU demos, including:

- WebGPU embedding benchmark: https://huggingface.co/spaces/Xenova/webgpu-embedding-benchm...

- Real-time object detection: https://huggingface.co/spaces/Xenova/webgpu-video-object-det...

- Real-time background removal: https://huggingface.co/spaces/Xenova/webgpu-video-background...

- WebGPU depth estimation: https://huggingface.co/spaces/Xenova/webgpu-depth-anything

- Image background removal: https://huggingface.co/spaces/Xenova/remove-background-webgp...

You can follow the progress for full WebGPU support in the v3 development branch (https://github.com/xenova/transformers.js/pull/545).

To answer your question, while there are certain ops missing, the main limitation at the moment is for models with decoders... which are not very fast (yet) due to inefficient buffer reuse and many redundant copies between CPU and GPU. We're working closely with the ORT team to fix these issues though!

New comment by xenova in "Transformers.js – Run Transformers directly in the browser"

xenova — Thu, 11 Apr 2024 14:58:23 +0000

Odd, the links seem to work for me. What error do you see? Can you try on a different network (e.g., mobile)?

New comment by xenova in "Transformers.js – Run Transformers directly in the browser"

xenova — Thu, 11 Apr 2024 13:34:34 +0000

We’ve put out a ton of demos that use much smaller models (10-60 MB), including:

- (44MB) In-browser background removal: https://huggingface.co/spaces/Xenova/remove-background-web. (We also put out a WebGPU version: https://huggingface.co/spaces/Xenova/remove-background-webgp...).

- (51MB) Whisper Web for automatic speech recognition: https://huggingface.co/spaces/Xenova/whisper-web (just select the quantized version in settings).

- (28MB) Depth Anything Web for monocular depth estimation: https://huggingface.co/spaces/Xenova/depth-anything-web

- (14MB) Segment Anything Web for image segmentation: https://huggingface.co/spaces/Xenova/segment-anything-web

- (20MB) Doodle Dash, an ML-powered sketch detection game: https://huggingface.co/spaces/Xenova/doodle-dash

… and many many more! Check out the Transformers.js demos collection for some others: https://huggingface.co/collections/Xenova/transformersjs-dem....

Models are cached on a per-domain basis (using the Web Cache API), meaning you don’t need to re-download the model on every page load. If you would like to persist the model across domains, you can create browser extensions with the library! :)

As for your last point, there are efforts underway, but nothing I can speak about yet!