Quantization made by Richard Erkhov.

Gemma2-9b-Max - GGUF

Model creator: https://huggingface.co/bunnycore/
Original model: https://huggingface.co/bunnycore/Gemma2-9b-Max/

Name	Quant method	Size
Gemma2-9b-Max.Q2_K.gguf	Q2_K	3.54GB
Gemma2-9b-Max.IQ3_XS.gguf	IQ3_XS	3.86GB
Gemma2-9b-Max.IQ3_S.gguf	IQ3_S	4.04GB
Gemma2-9b-Max.Q3_K_S.gguf	Q3_K_S	4.04GB
Gemma2-9b-Max.IQ3_M.gguf	IQ3_M	4.19GB
Gemma2-9b-Max.Q3_K.gguf	Q3_K	4.43GB
Gemma2-9b-Max.Q3_K_M.gguf	Q3_K_M	4.43GB
Gemma2-9b-Max.Q3_K_L.gguf	Q3_K_L	4.78GB
Gemma2-9b-Max.IQ4_XS.gguf	IQ4_XS	4.86GB
Gemma2-9b-Max.Q4_0.gguf	Q4_0	5.07GB
Gemma2-9b-Max.IQ4_NL.gguf	IQ4_NL	5.1GB
Gemma2-9b-Max.Q4_K_S.gguf	Q4_K_S	5.1GB
Gemma2-9b-Max.Q4_K.gguf	Q4_K	5.37GB
Gemma2-9b-Max.Q4_K_M.gguf	Q4_K_M	5.37GB
Gemma2-9b-Max.Q4_1.gguf	Q4_1	5.55GB
Gemma2-9b-Max.Q5_0.gguf	Q5_0	6.04GB
Gemma2-9b-Max.Q5_K_S.gguf	Q5_K_S	6.04GB
Gemma2-9b-Max.Q5_K.gguf	Q5_K	6.19GB
Gemma2-9b-Max.Q5_K_M.gguf	Q5_K_M	6.19GB
Gemma2-9b-Max.Q5_1.gguf	Q5_1	6.52GB
Gemma2-9b-Max.Q6_K.gguf	Q6_K	7.07GB
Gemma2-9b-Max.Q8_0.gguf	Q8_0	9.15GB

Original model description:

base_model:

ehristoforu/Gemma2-9B-it-psy10k-mental_health
bunnycore/HyperGemma-2-9B
crestf411/gemma2-9B-sunfall-v0.5.2
bunnycore/Gemma2-9b-Uncensored-Lora
IlyaGusev/gemma-2-9b-it-abliterated 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 bunnycore/HyperGemma-2-9B 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/HyperGemma-2-9B
  - model: crestf411/gemma2-9B-sunfall-v0.5.2+bunnycore/Gemma2-9b-Uncensored-Lora
  - model: IlyaGusev/gemma-2-9b-it-abliterated
  - model: ehristoforu/Gemma2-9B-it-psy10k-mental_health
merge_method: model_stock
base_model: bunnycore/HyperGemma-2-9B
dtype: bfloat16