You can deploy this model and start earning money today!

RichardErkhov/
wolf010_-_4TH_fine_tuned_Llama-3.2-3B-Instruct-gguf

Name: wolf010_-_4TH_fine_tuned_Llama-3.2-3B-Instruct-gguf
Availability: InStock

Views

No views yet

Quantization made by Richard Erkhov.

4TH_fine_tuned_Llama-3.2-3B-Instruct - GGUF

Name	Quant method	Size
4TH_fine_tuned_Llama-3.2-3B-Instruct.Q2_K.gguf	Q2_K	2.96GB
4TH_fine_tuned_Llama-3.2-3B-Instruct.IQ3_XS.gguf	IQ3_XS	3.28GB
4TH_fine_tuned_Llama-3.2-3B-Instruct.IQ3_S.gguf	IQ3_S	3.43GB
4TH_fine_tuned_Llama-3.2-3B-Instruct.Q3_K_S.gguf	Q3_K_S	3.41GB
4TH_fine_tuned_Llama-3.2-3B-Instruct.IQ3_M.gguf	IQ3_M	3.52GB
4TH_fine_tuned_Llama-3.2-3B-Instruct.Q3_K.gguf	Q3_K	3.74GB
4TH_fine_tuned_Llama-3.2-3B-Instruct.Q3_K_M.gguf	Q3_K_M	3.74GB
4TH_fine_tuned_Llama-3.2-3B-Instruct.Q3_K_L.gguf	Q3_K_L	4.03GB
4TH_fine_tuned_Llama-3.2-3B-Instruct.IQ4_XS.gguf	IQ4_XS	4.18GB
4TH_fine_tuned_Llama-3.2-3B-Instruct.Q4_0.gguf	Q4_0	4.34GB
4TH_fine_tuned_Llama-3.2-3B-Instruct.IQ4_NL.gguf	IQ4_NL	4.38GB
4TH_fine_tuned_Llama-3.2-3B-Instruct.Q4_K_S.gguf	Q4_K_S	4.37GB
4TH_fine_tuned_Llama-3.2-3B-Instruct.Q4_K.gguf	Q4_K	4.58GB
4TH_fine_tuned_Llama-3.2-3B-Instruct.Q4_K_M.gguf	Q4_K_M	4.58GB
4TH_fine_tuned_Llama-3.2-3B-Instruct.Q4_1.gguf	Q4_1	4.78GB
4TH_fine_tuned_Llama-3.2-3B-Instruct.Q5_0.gguf	Q5_0	5.21GB
4TH_fine_tuned_Llama-3.2-3B-Instruct.Q5_K_S.gguf	Q5_K_S	5.21GB
4TH_fine_tuned_Llama-3.2-3B-Instruct.Q5_K.gguf	Q5_K	5.34GB
4TH_fine_tuned_Llama-3.2-3B-Instruct.Q5_K_M.gguf	Q5_K_M	5.34GB
4TH_fine_tuned_Llama-3.2-3B-Instruct.Q5_1.gguf	Q5_1	5.65GB
4TH_fine_tuned_Llama-3.2-3B-Instruct.Q6_K.gguf	Q6_K	6.14GB
4TH_fine_tuned_Llama-3.2-3B-Instruct.Q8_0.gguf	Q8_0	7.95GB

Original model description:

base_model: MLP-KTLim/llama-3-Korean-Bllossom-8B language:

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