Quantization made by Richard Erkhov.

LLama-3.1-8B-HyperNova - GGUF

Model creator: https://huggingface.co/bunnycore/
Original model: https://huggingface.co/bunnycore/LLama-3.1-8B-HyperNova/

Name	Quant method	Size
LLama-3.1-8B-HyperNova.Q2_K.gguf	Q2_K	2.96GB
LLama-3.1-8B-HyperNova.IQ3_XS.gguf	IQ3_XS	3.28GB
LLama-3.1-8B-HyperNova.IQ3_S.gguf	IQ3_S	3.43GB
LLama-3.1-8B-HyperNova.Q3_K_S.gguf	Q3_K_S	3.41GB
LLama-3.1-8B-HyperNova.IQ3_M.gguf	IQ3_M	3.52GB
LLama-3.1-8B-HyperNova.Q3_K.gguf	Q3_K	3.74GB
LLama-3.1-8B-HyperNova.Q3_K_M.gguf	Q3_K_M	3.74GB
LLama-3.1-8B-HyperNova.Q3_K_L.gguf	Q3_K_L	4.03GB
LLama-3.1-8B-HyperNova.IQ4_XS.gguf	IQ4_XS	4.18GB
LLama-3.1-8B-HyperNova.Q4_0.gguf	Q4_0	4.34GB
LLama-3.1-8B-HyperNova.IQ4_NL.gguf	IQ4_NL	4.38GB
LLama-3.1-8B-HyperNova.Q4_K_S.gguf	Q4_K_S	4.37GB
LLama-3.1-8B-HyperNova.Q4_K.gguf	Q4_K	4.58GB
LLama-3.1-8B-HyperNova.Q4_K_M.gguf	Q4_K_M	4.58GB
LLama-3.1-8B-HyperNova.Q4_1.gguf	Q4_1	4.78GB
LLama-3.1-8B-HyperNova.Q5_0.gguf	Q5_0	5.21GB
LLama-3.1-8B-HyperNova.Q5_K_S.gguf	Q5_K_S	5.21GB
LLama-3.1-8B-HyperNova.Q5_K.gguf	Q5_K	5.34GB
LLama-3.1-8B-HyperNova.Q5_K_M.gguf	Q5_K_M	5.34GB
LLama-3.1-8B-HyperNova.Q5_1.gguf	Q5_1	5.65GB
LLama-3.1-8B-HyperNova.Q6_K.gguf	Q6_K	6.14GB
LLama-3.1-8B-HyperNova.Q8_0.gguf	Q8_0	7.95GB

Original model description:

base_model:

meta-llama/Meta-Llama-3.1-8B
bunnycore/HyperLLama3.1-8b-Nova
bunnycore/LLama-3.1-8b-Ultra-Max-Pro
DreadPoor/Heart_Stolen-8B-Model_Stock
grimjim/Llama-3.1-SuperNova-Lite-lorabilterated-8B
Replete-AI/Replete-LLM-V2-Llama-3.1-8b 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 meta-llama/Meta-Llama-3.1-8B 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: bunnycore/LLama-3.1-8b-Ultra-Max-Pro
  - model: DreadPoor/Heart_Stolen-8B-Model_Stock
  - model: bunnycore/HyperLLama3.1-8b-Nova
  - model: Replete-AI/Replete-LLM-V2-Llama-3.1-8b
  - model: grimjim/Llama-3.1-SuperNova-Lite-lorabilterated-8B
merge_method: model_stock
base_model: meta-llama/Meta-Llama-3.1-8B
dtype: bfloat16