vibevoice asr bitnet needs about 2.0 GB of memory at its main file (a 1.3 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 7 quants, from 0.0 GB to 1.6 GB.
VibeVoice-ASR-BitNet GGUF for real‑time CPU ASR
VibeVoice-ASR-BitNet is a compressed variant of VibeVoice-ASR optimized for real‑time inference on edge CPUs. The GGUF conversion uses ternary 2‑bit quantization for the LM projection weights and offers identical transcription quality across all variants. The model is licensed under MIT.
Good at
- Real‑time CPU inference
- Consistent transcription quality across variants
- Low VRAM footprint
Limits
- No GPU required but limited to CPU only
- No vision support
- No language metadata provided
Best for
- Edge devices needing real‑time speech recognition
- Low‑resource servers
- Embedded ASR applications
Who it’s for. Developers building speech‑to‑text solutions on CPUs with limited memory. The model is suitable for edge devices, IoT, and low‑power servers that require real‑time inference without GPU acceleration.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 0.0 GB | 0.5 GB | Fits | Get file → | |
| — | 1.1 GB | 1.7 GB | Fits | Get file → | |
| — | 1.2 GB | 1.8 GB | Fits | Get file → | |
| — | 1.3 GB | 2.0 GB | Fits | Get file → | |
| — | 1.4 GB | 2.1 GB | Fits | Get file → | |
| — | 1.4 GB | 2.1 GB | Fits | Get file → | |
| — | 1.6 GB | 2.3 GB | Fits | Get file → |
For 8 GB VRAM, the 1.1 GB file (est. 1.7 GB memory at 8 k context) is a good balance. If 4 GB VRAM is available, the 1.18 GB file (1.8 GB memory) works. For 2 GB VRAM, use the 1.32 GB file (2 GB memory). All variants use the same ternary quantization and produce identical output.
What GPU do you need for vibevoice asr bitnet?
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 the main file (1.6 GB file, about 2.3 GB in use).
Which vibevoice asr bitnet 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 asr bitnet
How much VRAM does vibevoice asr bitnet need?
About 2.0 GB at its main file with an 8K context window. That is the 1.3 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 bitnet on an 8 GB GPU?
Yes, with the smaller files: the 1.6 GB file needs about 2.3 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of vibevoice asr bitnet GGUF?
It depends on the quant: file is 0.0 GB, file is 1.1 GB, file is 1.2 GB, file is 1.3 GB, file is 1.4 GB, file is 1.4 GB and 1 more.
Where can I download vibevoice asr bitnet GGUF?
The files are on Hugging Face in the cstr/vibevoice-asr-bitnet-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 bitnet 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.
Does the model support multiple languages?
The model does not provide language metadata; it is intended for general ASR without explicit language tagging.
Is a GPU required for inference?
No, the model is designed for real‑time inference on edge CPUs and does not require a GPU.