Skip to content

Beta: real launches, updated every morning. Rankings may change while we tune them.

Haru 4B

Haru-4B is a low-latency and multilingual full-duplex continuous spoken dialogue foundation model: it listens and speaks at the same time, the way people do on a phone call. It is a pretrained base model, released for research. The code is at : a PyTorch implementation with a web demo, an MLX implementation with a native macOS app, and a plugin for serving with vLLM-Omni.

17Today’s rankDown 8 places since yesterday

Haru 4B launched on 12 November 2026. It ranked #17 on Daily Launch on 20 November 2026 with a Launch Score of 68, from trending score 311 on Hugging Face. It moved down 8 places from the day before.

Visit siteTrending on Hugging Face · trending score 311, 3.7k likes
Share

What is Haru 4B?

Haru 4B is a model by higurashi-ai on Hugging Face. It is released under the Apache 2.0 license.

How to get Haru 4B

pip install -e ./haru

From its model card on Hugging Face

More steps and the source are in its model card on Hugging Face.

Daily Launch card for Haru 4B

Launch timeline

  1. Hugging FacePublished on Hugging Face

  2. Hugging FaceTrending score 229, ranked #42 on Daily Launch

  3. Hugging FaceTrending score 317, ranked #19 on Daily Launch

  4. Hugging FaceTrending score 403, ranked #8 on Daily Launch

  5. Hugging FaceTrending score 420, ranked #5 on Daily Launch

  6. Hugging FaceTrending score 285, ranked #9 on Daily Launch

  7. Hugging FaceTrending score 311, ranked #17 on Daily Launch

Launch Score, last 7 days

05010014 Nov: 014 Nov15 Nov: 4215 Nov16 Nov: 6016 Nov17 Nov: 7117 Nov18 Nov: 7718 Nov19 Nov: 6919 Nov20 Nov: 6820 Nov68 today
Launch Score, 0 to 100. Days it was not ranked show 0.

#16 of 226 in the roundup for the week of 16-22 November 2026.

Similar new launches