Haru-4B
Released
2026-11-13
Last refreshed
2026-11-19
Status
Researched today
Open sourceCommercial use: permitted
Haru-4B is a released general LLM work model with open-source; evaluate it while provider pricing coverage matures.
Higurashi releases · 1 in the last 12 monthsChangelog →
Specifications
- Family
- Haru
- Released
- 2026-11-13
- Specialization
- speech-to-speech
- Openness
- Open source
- License
- Apache 2.0OSI-approvedPermitted
- Weights
- Available
- Code
- Unknown
- Training
- Pretrained
Pricing
No tracked provider pricing is available yet.
Links
Pricing
No tracked provider pricing is available yet.
Links
About
Haru-4B is Higurashi’s pretrained full-duplex spoken-dialogue model. It listens and speaks simultaneously through synchronized audio and text streams, learning conversational turn-taking and backchannels from real speech. Public code and weights support local research and fine-tuning.
Providers
No active provider routes are tracked for this model yet.
Capabilities
Audio
Benchmark peer barsfor Coding
No task-mapped benchmark peers are available for this model yet.
Migration checks
No linked migration route is available for this model yet.