---
tags:
- experimental
- testing
- gguf
- roleplay
- multimodal
- vision
- llava
---
# #Roleplay #Multimodal #Vision

**These are quants for an experimental model.**

    quantization_options = [
        "Q4_K_M", "Q4_K_S", "IQ4_XS",
        "Q5_K_M", "Q5_K_S",
        "Q6_K", "Q8_0"
    ]

Original model weights and information: <br> https://huggingface.co./Nitral-AI/Eris_PrimeV4.69-Vision-32k-7B

MMPROJ: <br> [./mmproj/mmproj-model-f16.gguf](./mmproj/mmproj-model-f16.gguf)

![image/png](https://cdn-uploads.huggingface.co/production/uploads/65d4cf2693a0a3744a27536c/ZKTLoWLodd7ixVaU4xZbq.png)

# Vision/multimodal capabilities:

 If you want to use vision functionality:

 * You must use the latest version of [KoboldCpp](https://github.com/LostRuins/koboldcpp).
 
To use the multimodal capabilities of this model and use **vision** you need to load the specified **mmproj** file, this can be found inside this model repo.
 
 * You can load the **mmproj** by using the corresponding section in the interface:

 ![image/png](https://cdn-uploads.huggingface.co/production/uploads/65d4cf2693a0a3744a27536c/UX6Ubss2EPNAT3SKGMLe0.png)