---
library_name: llama.cpp
license: mit
tags:
- gguf
- bf16
base_model:
- CrucibleLab/M3.2-24B-Loki-V1.3
---
# M3.2-24B-Loki-V1.3-GGUF

GGUF model files for `M3.2-24B-Loki-V1.3`.

This repository contains GGUF models quantized using [`llama.cpp`](https://github.com/ggerganov/llama.cpp).

- **Base Model:** `M3.2-24B-Loki-V1.3`
- **Quantization Methods Processed in this Job:** `Q8_0`, `Q6_K`, `Q5_K_M`, `Q5_0`, `Q5_K_S`, `Q4_K_M`, `Q4_K_S`, `Q4_0`, `Q3_K_L`, `Q3_K_M`, `Q3_K_S`, `Q2_K`, `BF16`
- **Importance Matrix Used:** No

This specific upload is for the **`BF16`** quantization.