---
license: cc-by-4.0
---
GGUF-IQ-Imatrix quants for **cgato/L3-TheSpice-8b-v0.1.3** as requested in [#29](https://huggingface.co./Lewdiculous/Model-Requests/discussions/29).

> [!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. <br>
> Use **KoboldCpp version 1.64** or higher.

> [!NOTE]
> Use the **ChatML** presets.

"Possibly more human and better at RP based on llama3."

![image/png](https://cdn-uploads.huggingface.co/production/uploads/65d4cf2693a0a3744a27536c/VNpZl0O7dpwWLK8i5RG5d.png)