# Pony V7 GGUFs

Install the ComfyUI [GGUF nodes by City96](https://github.com/city96/ComfyUI-GGUF) before using these workflows.

We recommend Q8_0 for the best balance between quality and file size.

| VARIANT | MAX VRAM |
|---------|------|
| F16 | ~16GB |
| [Q8_0](base-v7-Q8_0.gguf) | ~10GB |
| Q6_K | ~8GB |
| Q5_K_M | ~7GB |
| [Q4_0](base-v7-Q4_0.gguf) | ~6.5GB |
| Q4_K_M | ~6.5GB |
| Q3_K_L | ~6GB |
| Q3_K_S | ~6GB |
| Q2_K | ~5GB |

Download ComfyUI workflow for GGUF [here](../workflows/poly-v7-gguf.png).

![GGUF comparison](comparison.png)