MoonRide/Llama-3.2-3B-Khelavaster-GGUF

Experimental merge of multiple Llama 3.2 3B models, guided by MoonRide-Index-v7. Created with mergekit.

GGUFs made with llama.cpp (b4855). Calibration file used for creating imatrix: calibration_datav3.txt.

For best quality use Q8_0 or Q6_K quant.

GGUF

Model size

3.61B params

Architecture

llama

4-bit

5-bit

6-bit

8-bit

16-bit

Inference Providers NEW

This model is not currently available via any of the supported Inference Providers.

Model tree for MoonRide/Llama-3.2-3B-Khelavaster-GGUF

Base model

Quantized

(3)

this model