Edit model card

Llamacpp Quantizations of llama-3-Korean-Bllossom-70B(Quantization less than 40GB)

Using llama.cpp release b4048 for quantization.

Original model: https://huggingface.co/Bllossom/llama-3-Korean-Bllossom-70B

Downloads last month
456
GGUF
Model size
70.6B params
Architecture
llama

2-bit

3-bit

4-bit

Inference Examples
Unable to determine this model's library. Check the docs .

Model tree for legenduck/llama-3-Korean-Bllossom-70B-GGUF

Quantized
(2)
this model