Quantization made by Richard Erkhov.

llama_32_3b_ft_comfort_cove_merged - GGUF

Model creator: https://huggingface.co/rath1991/
Original model: https://huggingface.co/rath1991/llama_32_3b_ft_comfort_cove_merged/

Name	Quant method	Size
llama_32_3b_ft_comfort_cove_merged.Q2_K.gguf	Q2_K	1.27GB
llama_32_3b_ft_comfort_cove_merged.IQ3_XS.gguf	IQ3_XS	1.38GB
llama_32_3b_ft_comfort_cove_merged.IQ3_S.gguf	IQ3_S	1.44GB
llama_32_3b_ft_comfort_cove_merged.Q3_K_S.gguf	Q3_K_S	1.44GB
llama_32_3b_ft_comfort_cove_merged.IQ3_M.gguf	IQ3_M	1.49GB
llama_32_3b_ft_comfort_cove_merged.Q3_K.gguf	Q3_K	1.57GB
llama_32_3b_ft_comfort_cove_merged.Q3_K_M.gguf	Q3_K_M	1.57GB
llama_32_3b_ft_comfort_cove_merged.Q3_K_L.gguf	Q3_K_L	1.69GB
llama_32_3b_ft_comfort_cove_merged.IQ4_XS.gguf	IQ4_XS	1.71GB
llama_32_3b_ft_comfort_cove_merged.Q4_0.gguf	Q4_0	1.79GB
llama_32_3b_ft_comfort_cove_merged.IQ4_NL.gguf	IQ4_NL	1.79GB
llama_32_3b_ft_comfort_cove_merged.Q4_K_S.gguf	Q4_K_S	1.8GB
llama_32_3b_ft_comfort_cove_merged.Q4_K.gguf	Q4_K	1.88GB
llama_32_3b_ft_comfort_cove_merged.Q4_K_M.gguf	Q4_K_M	1.88GB
llama_32_3b_ft_comfort_cove_merged.Q4_1.gguf	Q4_1	1.95GB
llama_32_3b_ft_comfort_cove_merged.Q5_0.gguf	Q5_0	2.11GB
llama_32_3b_ft_comfort_cove_merged.Q5_K_S.gguf	Q5_K_S	2.11GB
llama_32_3b_ft_comfort_cove_merged.Q5_K.gguf	Q5_K	2.16GB
llama_32_3b_ft_comfort_cove_merged.Q5_K_M.gguf	Q5_K_M	2.16GB
llama_32_3b_ft_comfort_cove_merged.Q5_1.gguf	Q5_1	2.28GB
llama_32_3b_ft_comfort_cove_merged.Q6_K.gguf	Q6_K	2.46GB
llama_32_3b_ft_comfort_cove_merged.Q8_0.gguf	Q8_0	3.19GB

Original model description:

base_model: unsloth/llama-3.2-3b-instruct-bnb-4bit language: - en license: apache-2.0 tags: - text-generation-inference - transformers - unsloth - llama - trl

Uploaded model

Developed by: rath1991
License: apache-2.0
Finetuned from model : unsloth/llama-3.2-3b-instruct-bnb-4bit

This llama model was trained 2x faster with Unsloth and Huggingface's TRL library.

Additional thanks to @nicoboss for giving me access to his private supercomputer, enabling me to provide many more quants, at much higher speed, than I would otherwise be able to.