VibeVoice-ASR-Streaming-7B needs about 11.5 GB of memory at Q8_0 (a 9.9 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 3 quants, from 5.9 GB (Q4_K) to 17.4 GB (BF16).
7B parameter streaming ASR model with speaker attribution
VibeVoice-ASR-Streaming-7B is a 7 billion‑parameter audio model that transcribes speech in real time, attributing each segment to the speaker. It supports customized hotwords and ten languages. The model is released under the MIT license.
Good at
- Real‑time speaker‑attributed transcription
- Hotword customization
- Multilingual support
Limits
- No vision support
- Requires 8 k context for memory estimates
- No explicit language list beyond ten languages
Best for
- Live podcast transcription
- Voice‑controlled assistants
- Multilingual call center analytics
Who it’s for. Developers building real‑time speech recognition services that need speaker attribution and hotword support. The model is suitable for applications requiring low latency and multilingual coverage.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_K | 5.9 GB | 7.1 GB | Fits | Get file → | |
| Q8_0 | 9.9 GB | 11.5 GB | Too big | Get file → | |
| BF16 | 17.4 GB | 19.9 GB | Too big | Get file → |
For 8 GB VRAM use Q4_K (5.86 GB, ~7.1 GB memory at 8 k context). For 12 GB VRAM use Q8_0 (9.86 GB, ~11.5 GB memory). For larger memory budgets use BF16 (17.36 GB, ~19.9 GB).
What GPU do you need for VibeVoice-ASR-Streaming-7B?
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: no quant fits at an 8K context.
- 6 GB VRAM: no quant fits at an 8K context.
- 8 GB VRAM: the best quant that fits is Q4_K (5.9 GB file, about 7.1 GB in use).
- 12 GB VRAM: the best quant that fits is Q8_0 (9.9 GB file, about 11.5 GB in use).
- 16 GB VRAM: the best quant that fits is Q8_0 (9.9 GB file, about 11.5 GB in use).
- 24 GB VRAM: the best quant that fits is BF16 (17.4 GB file, about 19.9 GB in use).
Which VibeVoice-ASR-Streaming-7B quant should you choose?
Q8_0 (9.9 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 5.9 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
Source
Frequently asked questions about VibeVoice-ASR-Streaming-7B
How much VRAM does VibeVoice-ASR-Streaming-7B need?
About 11.5 GB at Q8_0 with an 8K context window. That is the 9.9 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-7B on an 8 GB GPU?
Yes, with Q4_K: the 5.9 GB file needs about 7.1 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of VibeVoice-ASR-Streaming-7B GGUF?
It depends on the quant: Q4_K is 5.9 GB, Q8_0 is 9.9 GB, BF16 is 17.4 GB.
Where can I download VibeVoice-ASR-Streaming-7B GGUF?
The files are on Hugging Face in the audio-cpp/VibeVoice-ASR-Streaming-7B-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-7B 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-7B on 8 GB VRAM?
Yes, the Q4_K quantized model is 5.86 GB and requires about 7.1 GB of VRAM at 8 k context.
Does the model support custom hotwords?
Yes, it supports customized hotwords to improve domain‑specific recognition.
What languages are supported?
It supports Chinese, English, French, German, Italian, Japanese, Korean, Portuguese, Russian, and Spanish.