RichardErkhov/Orion-zhen_-_Reflection-Llama3.2-3B-Instruct-gguf

Quantization made by Richard Erkhov.

Github

Discord

Request more models

Reflection-Llama3.2-3B-Instruct - GGUF

• Model creator: https://huggingface.co/Orion-zhen/
• Original model: https://huggingface.co/Orion-zhen/Reflection-Llama3.2-3B-Instruct/

Name	Quant method	Size
Reflection-Llama3.2-3B-Instruct.Q2_K.gguf	Q2_K	1.27GB
Reflection-Llama3.2-3B-Instruct.Q3_K_S.gguf	Q3_K_S	1.44GB
Reflection-Llama3.2-3B-Instruct.Q3_K.gguf	Q3_K	1.57GB
Reflection-Llama3.2-3B-Instruct.Q3_K_M.gguf	Q3_K_M	1.57GB
Reflection-Llama3.2-3B-Instruct.Q3_K_L.gguf	Q3_K_L	1.69GB
Reflection-Llama3.2-3B-Instruct.IQ4_XS.gguf	IQ4_XS	1.71GB
Reflection-Llama3.2-3B-Instruct.Q4_0.gguf	Q4_0	1.79GB
Reflection-Llama3.2-3B-Instruct.IQ4_NL.gguf	IQ4_NL	1.79GB
Reflection-Llama3.2-3B-Instruct.Q4_K_S.gguf	Q4_K_S	1.8GB
Reflection-Llama3.2-3B-Instruct.Q4_K.gguf	Q4_K	1.88GB
Reflection-Llama3.2-3B-Instruct.Q4_K_M.gguf	Q4_K_M	1.88GB
Reflection-Llama3.2-3B-Instruct.Q4_1.gguf	Q4_1	1.95GB
Reflection-Llama3.2-3B-Instruct.Q5_0.gguf	Q5_0	2.11GB
Reflection-Llama3.2-3B-Instruct.Q5_K_S.gguf	Q5_K_S	2.11GB
Reflection-Llama3.2-3B-Instruct.Q5_K.gguf	Q5_K	2.16GB
Reflection-Llama3.2-3B-Instruct.Q5_K_M.gguf	Q5_K_M	2.16GB
Reflection-Llama3.2-3B-Instruct.Q5_1.gguf	Q5_1	2.28GB
Reflection-Llama3.2-3B-Instruct.Q6_K.gguf	Q6_K	2.46GB
Reflection-Llama3.2-3B-Instruct.Q8_0.gguf	Q8_0	3.19GB

Original model description:

license: llama3.2 datasets: - isaiahbjork/reflection-40k-sharegpt - dvilasuero/reflection-v1-final-dedup language: - en base_model: - meta-llama/Llama-3.2-3B-Instruct pipeline_tag: text-generation tags: - reflection

Reflection-Llama3.2-3B-Instruct

Reflection is all you need! 😂