vibevoice.cpp models needs about 0.5 GB of memory at its main file (a 0.0 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 6 quants, from 0.0 GB to 13.9 GB (Q8_0).
VibeVoice‑cpp ASR model for long‑form audio transcription
VibeVoice‑cpp is a quantized speech‑to‑text model that can process up to 60 minutes of audio in a single pass. It outputs structured transcriptions with speaker, timestamp, and content, and supports over 50 languages and custom hotwords.
Good at
- 60‑minute single‑pass ASR
- Structured Who/When/What output
- Multilingual and code‑switching
Limits
- No vision support
- Requires 8‑k context for memory estimates
- MIT license limits commercial use to MIT terms
Best for
- Transcribing long meetings
- Generating structured meeting notes
- Multilingual audio transcription
Who it’s for. Developers building voice‑enabled applications that need full‑hour audio transcription with speaker diarization and timestamping. Ideal for teams that require structured outputs without external APIs.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 0.0 GB | 0.5 GB | Fits | Get file → | |
| — | 0.0 GB | 0.5 GB | Fits | Get file → | |
| — | 0.0 GB | 0.5 GB | Fits | Get file → | |
| Q8_0 | 1.7 GB | 2.4 GB | Fits | Get file → | |
| Q4_K | 10.4 GB | 12.1 GB | Too big | Get file → | |
| Q8_0 | 13.9 GB | 16.1 GB | Too big | Get file → |
For 8 GB VRAM, use the Q8_0 quantized file (1.7 GB, ~2.4 GB memory at 8k context). If 16 GB VRAM is available, the larger Q8_0 (13.93 GB, ~16.1 GB memory) provides higher fidelity. The Q4_K model (10.39 GB, ~12.1 GB memory) is suitable for 12–16 GB VRAM setups.
What GPU do you need for vibevoice.cpp models?
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 Q8_0 (1.7 GB file, about 2.4 GB in use).
- 6 GB VRAM: the best quant that fits is Q8_0 (1.7 GB file, about 2.4 GB in use).
- 8 GB VRAM: the best quant that fits is Q8_0 (1.7 GB file, about 2.4 GB in use).
- 12 GB VRAM: the best quant that fits is Q8_0 (1.7 GB file, about 2.4 GB in use).
- 16 GB VRAM: the best quant that fits is Q4_K (10.4 GB file, about 12.1 GB in use).
- 24 GB VRAM: the best quant that fits is Q8_0 (13.9 GB file, about 16.1 GB in use).
Which vibevoice.cpp models quant should you choose?
If memory is tight, the smallest file is the first one in the table at 0.0 GB, with the quality trade-offs that come with fewer bits.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about vibevoice.cpp models
How much VRAM does vibevoice.cpp models need?
About 0.5 GB at its main file with an 8K context window. That is the 0.0 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.cpp models on an 8 GB GPU?
Yes, with Q8_0: the 1.7 GB file needs about 2.4 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of vibevoice.cpp models GGUF?
It depends on the quant: file is 0.0 GB, file is 0.0 GB, file is 0.0 GB, Q8_0 is 1.7 GB, Q4_K is 10.4 GB, Q8_0 is 13.9 GB.
Where can I download vibevoice.cpp models GGUF?
The files are on Hugging Face in the mudler/vibevoice.cpp-models 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.cpp models 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‑cpp on 8 GB VRAM?
Yes, the 1.7 GB Q8_0 model requires about 2.4 GB of VRAM at 8k context, well within 8 GB.
Does the model support multiple languages?
It supports over 50 languages and handles code‑switching natively without explicit language settings.
Is there a vision component?
No, VibeVoice‑cpp is an ASR model only and does not include vision capabilities.