RichardErkhov/bunnycore_-_Maverick-8B-gguf

Quantization made by Richard Erkhov.

Github

Discord

Request more models

Maverick-8B - GGUF

• Model creator: https://huggingface.co/bunnycore/
• Original model: https://huggingface.co/bunnycore/Maverick-8B/

Name	Quant method	Size
Maverick-8B.Q2_K.gguf	Q2_K	2.46GB
Maverick-8B.IQ3_XS.gguf	IQ3_XS	3.28GB
Maverick-8B.IQ3_S.gguf	IQ3_S	3.43GB
Maverick-8B.Q3_K_S.gguf	Q3_K_S	3.41GB
Maverick-8B.IQ3_M.gguf	IQ3_M	3.52GB
Maverick-8B.Q3_K.gguf	Q3_K	3.74GB
Maverick-8B.Q3_K_M.gguf	Q3_K_M	3.74GB
Maverick-8B.Q3_K_L.gguf	Q3_K_L	4.03GB
Maverick-8B.IQ4_XS.gguf	IQ4_XS	4.18GB
Maverick-8B.Q4_0.gguf	Q4_0	4.34GB
Maverick-8B.IQ4_NL.gguf	IQ4_NL	4.38GB
Maverick-8B.Q4_K_S.gguf	Q4_K_S	4.37GB
Maverick-8B.Q4_K.gguf	Q4_K	4.58GB
Maverick-8B.Q4_K_M.gguf	Q4_K_M	4.58GB
Maverick-8B.Q4_1.gguf	Q4_1	4.78GB
Maverick-8B.Q5_0.gguf	Q5_0	5.21GB
Maverick-8B.Q5_K_S.gguf	Q5_K_S	5.21GB
Maverick-8B.Q5_K.gguf	Q5_K	5.34GB
Maverick-8B.Q5_K_M.gguf	Q5_K_M	5.34GB
Maverick-8B.Q5_1.gguf	Q5_1	5.65GB
Maverick-8B.Q6_K.gguf	Q6_K	6.14GB
Maverick-8B.Q8_0.gguf	Q8_0	7.95GB

Original model description:

license: llama3 tags: - merge - mergekit - lazymergekit

Maverick-8B

Maverick-8B is a merge of the following models using mergekit:

🧩 Configuration

models:
  - model: bunnycore/Cognitron-8B
  - model: failspy/Llama-3-8B-Instruct-abliterated
  - model: TIGER-Lab/MAmmoTH2-8B-Plus
merge_method: model_stock
base_model: bunnycore/Cognitron-8B
dtype: bfloat16