---
tags:
- roleplay
- llama3
- sillytavern
language:
- en
---
**"It keeps getting better!"**
"One of the top recent performers in the **Chaiverse Leaderboard**!"
GGUF-IQ-Imatrix quants for [ChaoticNeutrals/Poppy_Porpoise-v0.7-L3-8B](https://huggingface.co/ChaoticNeutrals/Poppy_Porpoise-v0.7-L3-8B).
> [!IMPORTANT]
> **Updated!**
> These quants have been redone with the fixes from [llama.cpp/pull/6920](https://github.com/ggerganov/llama.cpp/pull/6920) in mind.
> [!WARNING]
> Compatible SillyTavern presets [here (recommended/simple)](https://huggingface.co/ChaoticNeutrals/Poppy_Porpoise-v0.7-L3-8B/tree/main/Official%20Poppy%20Porpoise%20ST%20Presets)) or [here (Virt's)](https://huggingface.co/Virt-io/SillyTavern-Presets).
> Use the latest version of KoboldCpp. **Use the provided presets.**
> This is all still highly experimental, let the authors know how it performs for you, feedback is more important than ever now.
> [!NOTE]
> For **8GB VRAM** GPUs, I recommend the **Q4_K_M-imat** quant for up to 12288 context sizes.
**Original model information:**
# Update: Vision/multimodal capabilities again!
If you want to use vision functionality:
* You must use the latest versions 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. https://huggingface.co/ChaoticNeutrals/Llava_1.5_Llama3_mmproj
* You can load the **mmproj** by using the corresponding section in the interface:
