RichardErkhov/saqada_-_Llama-3.2-3B-Instruct-16bit-merged_lora_adapters-MOV-gguf

Quantization made by Richard Erkhov.

Github

Discord

Request more models

Llama-3.2-3B-Instruct-16bit-merged_lora_adapters-MOV - GGUF

• Model creator: https://huggingface.co/saqada/
• Original model: https://huggingface.co/saqada/Llama-3.2-3B-Instruct-16bit-merged_lora_adapters-MOV/

Name	Quant method	Size
Llama-3.2-3B-Instruct-16bit-merged_lora_adapters-MOV.Q2_K.gguf	Q2_K	1.27GB
Llama-3.2-3B-Instruct-16bit-merged_lora_adapters-MOV.Q3_K_S.gguf	Q3_K_S	1.44GB
Llama-3.2-3B-Instruct-16bit-merged_lora_adapters-MOV.Q3_K.gguf	Q3_K	1.57GB
Llama-3.2-3B-Instruct-16bit-merged_lora_adapters-MOV.Q3_K_M.gguf	Q3_K_M	1.57GB
Llama-3.2-3B-Instruct-16bit-merged_lora_adapters-MOV.Q3_K_L.gguf	Q3_K_L	1.69GB
Llama-3.2-3B-Instruct-16bit-merged_lora_adapters-MOV.IQ4_XS.gguf	IQ4_XS	1.71GB
Llama-3.2-3B-Instruct-16bit-merged_lora_adapters-MOV.Q4_0.gguf	Q4_0	1.79GB
Llama-3.2-3B-Instruct-16bit-merged_lora_adapters-MOV.IQ4_NL.gguf	IQ4_NL	1.79GB
Llama-3.2-3B-Instruct-16bit-merged_lora_adapters-MOV.Q4_K_S.gguf	Q4_K_S	1.8GB
Llama-3.2-3B-Instruct-16bit-merged_lora_adapters-MOV.Q4_K.gguf	Q4_K	1.88GB
Llama-3.2-3B-Instruct-16bit-merged_lora_adapters-MOV.Q4_K_M.gguf	Q4_K_M	1.88GB
Llama-3.2-3B-Instruct-16bit-merged_lora_adapters-MOV.Q4_1.gguf	Q4_1	1.95GB
Llama-3.2-3B-Instruct-16bit-merged_lora_adapters-MOV.Q5_0.gguf	Q5_0	2.11GB
Llama-3.2-3B-Instruct-16bit-merged_lora_adapters-MOV.Q5_K_S.gguf	Q5_K_S	2.11GB
Llama-3.2-3B-Instruct-16bit-merged_lora_adapters-MOV.Q5_K.gguf	Q5_K	2.16GB
Llama-3.2-3B-Instruct-16bit-merged_lora_adapters-MOV.Q5_K_M.gguf	Q5_K_M	2.16GB
Llama-3.2-3B-Instruct-16bit-merged_lora_adapters-MOV.Q5_1.gguf	Q5_1	2.28GB
Llama-3.2-3B-Instruct-16bit-merged_lora_adapters-MOV.Q6_K.gguf	Q6_K	2.46GB
Llama-3.2-3B-Instruct-16bit-merged_lora_adapters-MOV.Q8_0.gguf	Q8_0	3.19GB

Original model description:

base_model: unsloth/Llama-3.2-3B-Instruct language: - en license: apache-2.0 tags: - text-generation-inference - transformers - unsloth - llama - trl - sft

Uploaded model

• Developed by: saqada
• License: apache-2.0
• Finetuned from model : unsloth/Llama-3.2-3B-Instruct

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