Quantization made by Richard Erkhov.

LLama-3.1-4B-TitanFusion - GGUF

Model creator: https://huggingface.co/bunnycore/
Original model: https://huggingface.co/bunnycore/LLama-3.1-4B-TitanFusion/

Name	Quant method	Size
LLama-3.1-4B-TitanFusion.Q2_K.gguf	Q2_K	1.71GB
LLama-3.1-4B-TitanFusion.Q3_K_S.gguf	Q3_K_S	1.96GB
LLama-3.1-4B-TitanFusion.Q3_K.gguf	Q3_K	2.14GB
LLama-3.1-4B-TitanFusion.Q3_K_M.gguf	Q3_K_M	2.14GB
LLama-3.1-4B-TitanFusion.Q3_K_L.gguf	Q3_K_L	2.3GB
LLama-3.1-4B-TitanFusion.IQ4_XS.gguf	IQ4_XS	2.38GB
LLama-3.1-4B-TitanFusion.Q4_0.gguf	Q4_0	1.97GB
LLama-3.1-4B-TitanFusion.IQ4_NL.gguf	IQ4_NL	2.49GB
LLama-3.1-4B-TitanFusion.Q4_K_S.gguf	Q4_K_S	2.48GB
LLama-3.1-4B-TitanFusion.Q4_K.gguf	Q4_K	2.59GB
LLama-3.1-4B-TitanFusion.Q4_K_M.gguf	Q4_K_M	2.19GB
LLama-3.1-4B-TitanFusion.Q4_1.gguf	Q4_1	2.71GB
LLama-3.1-4B-TitanFusion.Q5_0.gguf	Q5_0	2.95GB
LLama-3.1-4B-TitanFusion.Q5_K_S.gguf	Q5_K_S	2.95GB
LLama-3.1-4B-TitanFusion.Q5_K.gguf	Q5_K	3.01GB
LLama-3.1-4B-TitanFusion.Q5_K_M.gguf	Q5_K_M	2.33GB
LLama-3.1-4B-TitanFusion.Q5_1.gguf	Q5_1	3.19GB
LLama-3.1-4B-TitanFusion.Q6_K.gguf	Q6_K	1.93GB
LLama-3.1-4B-TitanFusion.Q8_0.gguf	Q8_0	4.47GB

Original model description:

base_model:

Magpie-Align/MagpieLM-4B-Chat-v0.1
anthracite-org/magnum-v2-4b
TheDrummer/Hubble-4B-v1 library_name: transformers tags:
mergekit
merge

merge

This is a merge of pre-trained language models created using mergekit.

Merge Details

Merge Method

This model was merged using the Model Stock merge method using Magpie-Align/MagpieLM-4B-Chat-v0.1 as a base.

Models Merged

The following models were included in the merge:

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: Magpie-Align/MagpieLM-4B-Chat-v0.1
  - model: anthracite-org/magnum-v2-4b
  - model: TheDrummer/Hubble-4B-v1
merge_method: model_stock
base_model: Magpie-Align/MagpieLM-4B-Chat-v0.1
dtype: bfloat16