pony v7 base needs about 4.9 GB of memory at Q4_0 (a 3.9 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 2 quants, from 3.9 GB (Q4_0) to 7.3 GB (Q8_0).
Pony V7 Base – a 6.86B character generation model
Pony V7 Base is a 6.86B parameter model built on the Aura architecture. It generates diverse character styles and handles interactions via natural language prompts. The model is available in GGUF format for efficient inference.
Good at
- Character generation
- Style versatility
- Natural language interaction
Limits
- No vision support
- Limited context length (8k tokens)
- License type: other
Best for
- Creating text-based characters
- Generating dialogue scripts
- Prototyping character interactions
Who it’s for. Developers and creators looking to build or extend character-based applications. The model is suited for those who need a versatile, text-only character generator.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_0 | 3.9 GB | 4.9 GB | Fits | Get file → | |
| Q8_0 | 7.3 GB | 8.7 GB | Too big | Get file → |
For 8 GB VRAM, use Q4_0 (file size 3.95 GB, estimated memory 4.9 GB at 8k context). For higher quality and 16 GB VRAM, use Q8_0 (file size 7.35 GB, estimated memory 8.7 GB at 8k context).
What GPU do you need for pony v7 base?
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: the best quant that fits is Q4_0 (3.9 GB file, about 4.9 GB in use).
- 8 GB VRAM: the best quant that fits is Q4_0 (3.9 GB file, about 4.9 GB in use).
- 12 GB VRAM: the best quant that fits is Q8_0 (7.3 GB file, about 8.7 GB in use).
Which pony v7 base quant should you choose?
Q4_0 (3.9 GB) is the middle option in this repository. 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 pony v7 base
How much VRAM does pony v7 base need?
About 4.9 GB at Q4_0 with an 8K context window. That is the 3.9 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 pony v7 base on an 8 GB GPU?
Yes, with Q4_0: the 3.9 GB file needs about 4.9 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of pony v7 base GGUF?
It depends on the quant: Q4_0 is 3.9 GB, Q8_0 is 7.3 GB.
Where can I download pony v7 base GGUF?
The files are on Hugging Face in the Runware/pony-v7-base repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does pony v7 base use?
Hugging Face lists the license as other. 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 Pony V7 Base on 8 GB VRAM?
Yes, the Q4_0 quantized model uses about 4.9 GB of VRAM at 8k context, fitting within an 8 GB GPU.
Does the model support image or video input?
No, Pony V7 Base is a text-only model and does not handle vision or multimodal inputs.
What is the recommended quant for best quality?
The Q8_0 quantized model offers the best quality while remaining manageable on GPUs with 16 GB VRAM.