vibevoice asr it yodas only ggml needs about 13.1 GB of memory at Q5_0 (a 11.3 GB file) with an 8K context window, so it fits on a 16 GB GPU. This repository has 3 quants, from 10.4 GB (Q4_0) to 13.9 GB (Q8_0).
vibevoice asr it yodas only ggml is a 8.67B-parameter Vibevoice model in GGUF format, quantized by LocalAI-io. The repository has 3 quant files, from 10.4 GB (Q4_0) to 13.9 GB (Q8_0).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_0 | 10.4 GB | 12.1 GB | Too big | Get file → | |
| Q5_0 | 11.3 GB | 13.1 GB | Too big | Get file → | |
| Q8_0 | 13.9 GB | 16.1 GB | Too big | Get file → |
What GPU do you need for vibevoice asr it yodas only ggml?
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: no quant fits at an 8K context.
- 12 GB VRAM: no quant fits at an 8K context.
- 16 GB VRAM: the best quant that fits is Q5_0 (11.3 GB file, about 13.1 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 asr it yodas only ggml quant should you choose?
Q5_0 (11.3 GB) is the middle option in this repository. Closer to the original model than 4-bit, for a moderate increase in size. A good pick when you have memory to spare.
If memory is tight, the smallest file is Q4_0 at 10.4 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 it yodas only ggml
How much VRAM does vibevoice asr it yodas only ggml need?
About 13.1 GB at Q5_0 with an 8K context window. That is the 11.3 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 it yodas only ggml on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 12.1 GB, so you would need a larger GPU or CPU offloading.
What is the file size of vibevoice asr it yodas only ggml GGUF?
It depends on the quant: Q4_0 is 10.4 GB, Q5_0 is 11.3 GB, Q8_0 is 13.9 GB.
Where can I download vibevoice asr it yodas only ggml GGUF?
The files are on Hugging Face in the LocalAI-io/vibevoice-asr-it-yodas-only-ggml 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 it yodas only ggml 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.