VI

VibeVoice ASR Streaming 1.5B

VibevoiceGGUF by christopherthompson81Updated 2026-09-20
Download on Hugging Face
Parameters3.1B
Context—
Layers—
Architectureaudiocpp
Smallest quant2.1 GB
Quick answer

VibeVoice ASR Streaming 1.5B needs about 4.2 GB of memory at Q8_0 (a 3.3 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 3 quants, from 2.1 GB (Q4_K) to 5.6 GB (BF16).

VibeVoice ASR Streaming 1.5B – 3.1B parameter audio model for speaker‑attributed transcription

VibeVoice ASR Streaming 1.5B is a 3.1‑billion‑parameter audio model that transcribes who spoke and what was said. It supports customized hotwords and ten languages. The model is released under the MIT license and is available as GGUF files for audio.cpp.

Good at

  • Streaming speaker‑attributed transcription
  • Custom hotword support
  • Multilingual (10 languages)

Limits

  • No vision support
  • Requires 8 k context for estimates
  • Large memory for BF16 quant

Best for

  • Live speech transcription
  • Voice‑activated assistants
  • Multilingual dictation

Who it’s for. Developers building real‑time ASR systems that need speaker attribution and hotword customization. The model is suitable for applications requiring accurate transcription across multiple languages.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K2.1 GB 2.9 GB
Fits Get file →
Q8_03.3 GB 4.2 GB
Fits Get file →
BF165.6 GB 6.8 GB
Fits Get file →

For 8 GB VRAM, use the Q4_K quant (2.12 GB, ~2.9 GB memory at 8 k context). For 12 GB VRAM, Q8_0 (3.34 GB, ~4.2 GB memory) is a good balance. BF16 (5.64 GB, ~6.8 GB memory) requires more memory but offers higher precision.

What GPU do you need for VibeVoice ASR Streaming 1.5B?

These figures add the file size, an fp16 KV cache at an 8K context window and about 0.5 GB for the runtime. They are estimates, so leave a little headroom, and expect to use less context or a smaller quant if you are right at the limit.

  • 4 GB VRAM: the best quant that fits is Q4_K (2.1 GB file, about 2.9 GB in use).
  • 6 GB VRAM: the best quant that fits is Q8_0 (3.3 GB file, about 4.2 GB in use).
  • 8 GB VRAM: the best quant that fits is BF16 (5.6 GB file, about 6.8 GB in use).

Which VibeVoice ASR Streaming 1.5B quant should you choose?

Q8_0 (3.3 GB) is the middle option in this repository. Close to lossless. It costs roughly twice the memory of a 4-bit file, so it suits cases where you have plenty of VRAM.

If memory is tight, the smallest file is Q4_K at 2.1 GB, with the quality trade-offs that come with fewer bits. The usual sweet spot between file size and quality, and the quant most people start with.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architectureaudiocpp
Parameters3.1B

Source

FamilyVibevoice
Licensemit
Downloads (HF)90,421
Last updated2026-09-20

Frequently asked questions about VibeVoice ASR Streaming 1.5B

How much VRAM does VibeVoice ASR Streaming 1.5B need?

About 4.2 GB at Q8_0 with an 8K context window. That is the 3.3 GB file, plus the KV cache and roughly 0.5 GB of runtime overhead. Smaller quants need less and longer context needs more.

Can I run VibeVoice ASR Streaming 1.5B on an 8 GB GPU?

Yes, with BF16: the 5.6 GB file needs about 6.8 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of VibeVoice ASR Streaming 1.5B GGUF?

It depends on the quant: Q4_K is 2.1 GB, Q8_0 is 3.3 GB, BF16 is 5.6 GB.

Where can I download VibeVoice ASR Streaming 1.5B GGUF?

The files are on Hugging Face in the christopherthompson81/VibeVoice-ASR-Streaming-1.5B-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does VibeVoice ASR Streaming 1.5B use?

Hugging Face lists the license as mit. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.

Can I run VibeVoice ASR Streaming 1.5B on 8 GB VRAM?

Yes, the Q4_K quant file is 2.12 GB and uses about 2.9 GB of VRAM at 8 k context, fitting within an 8 GB GPU.

Does the model support custom hotwords?

Yes, the model includes built‑in support for customized hotwords to improve domain‑specific recognition.

What languages does it support?

It supports Chinese, English, French, German, Italian, Japanese, Korean, Portuguese, Russian, and Spanish.

Other GGUFs of VibeVoice-ASR-Streaming-1.5B

Similar models

Browse all →

More from christopherthompson81

All by christopherthompson81 →

More Vibevoice models

All Vibevoice →

Other tiny models

All tiny models →